feat(diffusion): add QwenImage spatial-shard decode

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

.github/CODEOWNERS

@@ -1,6 +1,11 @@
 # CODEOWNERS is used to automatically assign PR reviewers
 # Format: path pattern @username or @team
 # More info: https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners
+#
+# The vllm_omni/** source-tree rules below are derived from the `owners` and
+# `primary_code_paths` front matter in docs/design/module/*.md. When updating
+# ownership, update the design doc first, then regenerate the matching rule here.
+# Last-match-wins: more specific rules must come AFTER broader ones.
 
 # Default owners (fallback reviewers for all files)
 * @Gaohan123 @hsliuustc0106 @ywang96
@@ -21,25 +26,10 @@
 # CI
 /.buildkite/ @yenuo26 @congw729 @NickCao
 
-# Engine and model_executor
+# ComfyUI / external apps
-/vllm_omni/core/ @tzhouam @yinpeiqi @fake0fan @Sy0307
+/apps/ @fhfuih @alex-jw-brooks
-/vllm_omni/engine/ @tzhouam @yinpeiqi @fake0fan @Sy0307
-/vllm_omni/entrypoints/ @tzhouam @yinpeiqi @fake0fan @alex-jw-brooks @NickCao
-/vllm_omni/model_executor/ @tzhouam @gcanlin
-/vllm_omni/worker/ @tzhouam @gcanlin
 
-# Diffusion
+# Benchmarks (out-of-tree)
-/vllm_omni/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @david6666666 @xuechendi
-/vllm_omni/lora/ @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @yuanheng-zhao
-
-# Diffusion CPU offloading
-/vllm_omni/diffusion/offloader/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @yuanheng-zhao @xuechendi
-
-# Omni and TTS support
-/vllm_omni/transformers_utils/ @tzhouam @yuanheng-zhao
-/vllm_omni/model_executor/models/ @linyueqian @ZeldaHuang @princepride @yuanheng-zhao @amy-why-3459 @Bounty-hunter @Sy0307 @gcanlin @NickCao
-
-# Benchmarks
 /benchmarks/accuracy/ @david6666666
 /benchmarks/build_dataset/ @linyueqian @yuanheng-zhao
 /benchmarks/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @xuechendi
@@ -47,20 +37,112 @@
 /benchmarks/glm_image/ @princepride @JaredforReal
 /benchmarks/tts/ @linyueqian @ZeldaHuang @princepride @Sy0307 @gcanlin
 
-# Usability and Observability
+# =====================================================================
-/vllm_omni/deploy/ @tzhouam @lishunyang12
+# Module design ownership (docs/design/module/*.md)
-/vllm_omni/metrics/ @lishunyang12
+# Each section header cites the source design doc.
-/vllm_omni/profiler/ @gcanlin
+# =====================================================================
 
-# ComfyUI
+# Autoregressive runtime — docs/design/module/ar_runtime.md
-/apps/ @fhfuih @alex-jw-brooks
+/vllm_omni/core/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
+/vllm_omni/worker/ @tzhouam @yinpeiqi @fake0fan @Sy0307 @Gaohan123
 
-# Large Scale Serving
+# Engine orchestration & stage runtime — docs/design/module/engine_orchestration.md, stage_runtime.md
+/vllm_omni/engine/ @tzhouam @fake0fan
+# File-level overrides: input/output modality contracts own these engine files
+# — docs/design/module/input_output_modality_contracts.md
+/vllm_omni/engine/messages.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/serialization.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/mm_outputs.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/output_modality.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/engine/output_processor.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+
+# Input/output modality contracts — docs/design/module/input_output_modality_contracts.md
+/vllm_omni/inputs/ @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/outputs/ @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/request.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+/vllm_omni/data_entry_keys.py @Sy0307 @amy-why-3459 @Gaohan123 @alex-jw-brooks
+
+# Entrypoints and serving boundaries — docs/design/module/entrypoints.md
+/vllm_omni/entrypoints/ @alex-jw-brooks @linyueqian @NickCao
+# File-level overrides within entrypoints/
+/vllm_omni/entrypoints/openai/errors.py @alex-jw-brooks @NickCao
+/vllm_omni/entrypoints/cli/benchmark/ @alex-jw-brooks @Bounty-hunter
+
+# Error contracts — docs/design/module/error_contracts.md
+/vllm_omni/errors.py @alex-jw-brooks @NickCao
+
+# OmniConnector (inter-stage transport) — docs/design/module/omni_connector.md
 /vllm_omni/distributed/ @princepride @yuanheng-zhao @xuechendi @natureofnature @fake0fan
 
-# Quantization and configuration
+# Model integration — docs/design/module/model_integration.md
+/vllm_omni/model_executor/ @tzhouam @gcanlin
+/vllm_omni/model_executor/models/ @tzhouam @gcanlin @Sy0307 @amy-why-3459 @linyueqian
+/vllm_omni/model_extras/ @tzhouam @gcanlin @princepride
+/vllm_omni/plugins/ @gcanlin @tjtanaa @xuechendi
+# Config override within model_executor — docs/design/module/vllm_omni_config.md
+/vllm_omni/model_executor/stage_configs/ @lishunyang12 @alex-jw-brooks
+
+# Execution platforms (hardware backends) — docs/design/module/execution_platforms.md
+/vllm_omni/platforms/ @gcanlin @tjtanaa @xuechendi
+/vllm_omni/attention/ @gcanlin @tjtanaa @xuechendi @david6666666 @lishunyang12
+
+# Configuration & deploy — docs/design/module/vllm_omni_config.md
 /vllm_omni/config/ @lishunyang12 @alex-jw-brooks
+/vllm_omni/deploy/ @lishunyang12 @alex-jw-brooks
+
+# Quantization — docs/design/module/quantization.md
 /vllm_omni/quantization/ @david6666666 @Isotr0py @lishunyang12
 
-# Hardware plugins and accelerators
+# Observability — docs/design/module/observability.md
-/vllm_omni/platforms/ @gcanlin @tjtanaa @xuechendi
+/vllm_omni/metrics/ @lishunyang12 @vraiti
+
+# Profiling — docs/design/module/profiling.md
+/vllm_omni/profiler/ @gcanlin
+
+# Benchmarking (in-tree) — docs/design/module/benchmarking.md
+/vllm_omni/benchmarks/ @alex-jw-brooks @Bounty-hunter
+
+# LoRA (no dedicated design doc; ownership intentionally narrowed)
+/vllm_omni/lora/ @SamitHuang @wtomin
+
+# Transformers utils (related path only in design docs; preserves prior ownership)
+/vllm_omni/transformers_utils/ @tzhouam @yuanheng-zhao
+
+# =====================================================================
+# Diffusion module family — docs/design/module/diffusion/
+# Umbrella rule first; sub-module rules after it win via last-match.
+# =====================================================================
+
+# Diffusion umbrella (top-level files: data.py, forward_context.py, etc.)
+# — docs/design/module/diffusion/index.md
+/vllm_omni/diffusion/ @Isotr0py @princepride @SamitHuang @wtomin @ZJY0516 @RuixiangMa @david6666666 @xuechendi
+
+# Cache management — docs/design/module/cache_management.md
+/vllm_omni/diffusion/cache/ @Isotr0py @princepride @SamitHuang
+
+# Diffusion quantization — docs/design/module/quantization.md
+/vllm_omni/diffusion/quantization/ @david6666666 @Isotr0py @lishunyang12
+
+# Diffusion profiling — docs/design/module/profiling.md
+/vllm_omni/diffusion/profiler/ @gcanlin
+
+# Diffusion runtime (scheduler, executor, worker)
+# — docs/design/module/diffusion/diffusion_runtime.md, continuous_batching.md
+/vllm_omni/diffusion/sched/ @Isotr0py @princepride @SamitHuang @fhfuih
+/vllm_omni/diffusion/executor/ @Isotr0py @princepride @SamitHuang @fhfuih
+/vllm_omni/diffusion/worker/ @Isotr0py @princepride @SamitHuang @fhfuih
+
+# Diffusion model integration (pipelines, registration, checkpoint loading)
+# — docs/design/module/diffusion/diffusion_model_integration.md
+/vllm_omni/diffusion/models/ @fhfuih @Bounty-hunter @wtomin
+/vllm_omni/diffusion/model_loader/ @fhfuih @Bounty-hunter @wtomin @RuixiangMa
+/vllm_omni/diffusion/lora/ @fhfuih @Bounty-hunter @wtomin @RuixiangMa
+
+# Diffusion parallelism (rank topology, TP/SP/PP/VAE patch)
+# — docs/design/module/diffusion/parallelism.md
+/vllm_omni/diffusion/distributed/ @princepride @yuanheng-zhao @xuechendi @Bounty-hunter
+/vllm_omni/diffusion/attention/parallel/ @princepride @yuanheng-zhao @xuechendi @Bounty-hunter
+
+# Diffusion offloader (CPU offloading, DLO)
+# — docs/design/module/diffusion/offloader.md
+/vllm_omni/diffusion/offloader/ @yuanheng-zhao @david6666666 @lishunyang12

.pre-commit-config.yaml

@@ -66,7 +66,10 @@ repos:
       entry: python tools/pre_commit/check_tts_adapter.py
       language: python
       pass_filenames: false
-      files: ^vllm_omni/entrypoints/openai/(serving_speech\.py|tts_adapters/__init__\.py)$
+      files: ^(vllm_omni/entrypoints/openai/(serving_speech\.py|tts_adapters/__init__\.py)|tools/pre_commit/check_tts_adapter\.py)$
+      # The budget-is-now-slack reminder is printed on a PASSING run, and
+      # pre-commit hides output from passing hooks unless the hook is verbose.
+      verbose: true
 
     # Keep `suggestion` last
     - id: suggestion

docs/.nav.yml

@@ -16,31 +16,21 @@ nav:
   - Examples:
     - examples/README.md
     - Offline Inference:
-      - GLM-Image Multistage End-to-End Inference: user_guide/examples/offline_inference/glm_image.md
-      - HunyuanImage-3.0 Image-to-Text Inference: user_guide/examples/offline_inference/hunyuan_image3.md
       - Image-To-Image: user_guide/examples/offline_inference/image_to_image.md
       - Image-To-Video: user_guide/examples/offline_inference/image_to_video.md
-      - InternVLA-A1: user_guide/examples/offline_inference/internvla_a1.md
+      - Speech-To-Video: user_guide/examples/offline_inference/speech_to_video.md
-      - MiMo-Audio: user_guide/examples/offline_inference/mimo_audio.md
-      - Qwen2.5-Omni: user_guide/examples/offline_inference/qwen2_5_omni.md
-      - Qwen3-Omni: user_guide/examples/offline_inference/qwen3_omni.md
       - Text-To-Audio: user_guide/examples/offline_inference/text_to_audio.md
       - Text-To-Image: user_guide/examples/offline_inference/text_to_image.md
       - Text-To-Speech: user_guide/examples/offline_inference/text_to_speech.md
       - Text-To-Video: user_guide/examples/offline_inference/text_to_video.md
+      - X-To-Text: user_guide/examples/offline_inference/x_to_text.md
       - X-To-Video-Audio: user_guide/examples/offline_inference/x_to_video_audio.md
     - Online Serving:
-      - BAGEL-7B-MoT: user_guide/examples/online_serving/bagel.md
-      - vLLM-Omni Helm Chart: user_guide/examples/online_serving/chart-helm.md
-      - Diffusers Backend Adapter: user_guide/examples/online_serving/diffusers_pipeline_adapter.md
-      - GLM-Image Online Serving: user_guide/examples/online_serving/glm_image.md
       - Image-To-Image: user_guide/examples/online_serving/image_to_image.md
       - Image-To-Video: user_guide/examples/online_serving/image_to_video.md
-      - MiMo-Audio: user_guide/examples/online_serving/mimo_audio.md
+      - Speech-To-Video: user_guide/examples/online_serving/speech_to_video.md
-      - Qwen2.5-Omni: user_guide/examples/online_serving/qwen2_5_omni.md
-      - Qwen3-Omni: user_guide/examples/online_serving/qwen3_omni.md
-      - Text-To-Speech: user_guide/examples/online_serving/text_to_speech.md
       - Text-To-Image: user_guide/examples/online_serving/text_to_image.md
+      - Text-To-Speech: user_guide/examples/online_serving/text_to_speech.md
       - Text-To-Video: user_guide/examples/online_serving/text_to_video.md
   - General:
     - usage/*

docs/design/feature/vae_parallel.md

@@ -449,20 +449,21 @@ Complete examples in the codebase:
 
 ---
 
-## Spatially-Sharded Decode (Wan)
+## Spatially-Sharded Decode (Wan and QwenImage)
 
-The tile-parallel executor above assigns independent spatial **tiles** to ranks. The Wan VAE additionally supports a **spatially-sharded decode** backend, selected through `DiffusionParallelConfig.vae_parallel_mode` (`"spatial_shard_height"` or `"spatial_shard_width"`; default is `"tile"`).
+The tile-parallel executor above assigns independent spatial **tiles** to ranks. The Wan VAE and distributed QwenImage backend additionally support a **spatially-sharded decode** backend. `DiffusionParallelConfig.vae_parallel_mode="auto"` is the default; explicit `"tile"`, `"spatial_shard_height"`, and `"spatial_shard_width"` modes remain available.
 
 ### How it differs from tile parallel
 
-| Aspect | Tile parallel (`"tile"`) | Spatially-sharded (`"spatial_shard_height"`/`"spatial_shard_width"`) |
+| Aspect | Tile parallel (`"tile"`) | Automatic (`"auto"`) | Spatially-sharded (`"spatial_shard_height"`/`"spatial_shard_width"`) |
-|--------|--------------------------|-----------------------------------------------|
+|--------|--------------------------|----------------------|-----------------------------------------------|
-| Unit of work | Independent overlapping tiles | A single global feature map sharded along H or W |
+| Unit of work | Independent overlapping tiles | Chooses tile or a spatial shard per request | A single global feature map sharded along H or W |
-| Cross-rank communication | Gather tiles to rank 0, stitch + blend | Per-conv **halo exchange** of boundary rows/cols (P2P) |
+| Cross-rank communication | Gather tiles to rank 0, stitch + blend | Depends on the selected path | Per-conv **halo exchange** of boundary rows/cols (P2P) |
-| Output assembly | Blend overlapping tiles | All-gather shards on rank 0, trim padding (matches `broadcast_result=False`) |
+| Output assembly | Blend overlapping tiles | Depends on the selected path | All-gather shards on rank 0 and trim padding; QwenImage then broadcasts |
-| Scope | Decode + encode | Decode only |
+| Activation memory | Bounded by tile size | Depends on the selected path | Grows with full output area divided across ranks |
+| Scope | Decode + encode | Wan/QwenImage decode selection; encode remains tiled | Decode only |
 
-Spatial-shard decode swaps the decoder's spatial convolutions/padding for halo-exchanging variants (`WanDistConv2d`, `WanDistCausalConv3d`, `WanDistZeroPad2d`) so each rank only holds a shard of the activations but still sees the correct receptive field at shard boundaries. Implementation lives in `vllm_omni/diffusion/distributed/autoencoders/wan_spatial_shard.py`.
+Spatial-shard decode swaps the decoder's spatial convolutions/padding for context-aware halo-exchanging variants so each rank only holds a shard of the activations but still sees the correct receptive field at shard boundaries. Wan and QwenImage share the padding, 2D convolution, attention, halo, and trim primitives in `wan_spatial_shard.py`; `qwenimage_spatial_shard.py` supplies a causal-convolution subclass that remains discoverable by Diffusers' QwenImage cache accounting.
 
 ### Wiring
 
@@ -473,15 +474,17 @@ serve.py (--vae-parallel-mode) / OmniEngineArgs
   -> DiffusionParallelConfig.vae_parallel_mode
   -> registry.py: model.vae.set_parallel_size(vae_pp_size, mode=...)
   -> DistributedVaeExecutor.parallel_mode
-  -> DistributedAutoencoderKLWan.tiled_decode dispatch
+  -> capability-based pipeline preparation
+  -> DistributedAutoencoderKLWan/DistributedAutoencoderKLQwenImage.tiled_decode dispatch
 ```
 
-`DistributedAutoencoderKLWan._spatial_shard_decode_enabled()` gates the path: it requires distributed decode to be enabled, a 5D latent, and `vae_patch_parallel_size == DiT group size`. Otherwise it logs a warning and falls back to tile-parallel decode.
+The shared spatial policy gates the path: it requires distributed decode to be enabled, a 5D latent, a supported VAE capability, and `vae_patch_parallel_size == DiT group size`. The method is reached only after Diffusers has selected tiled decode for the request. In `auto` mode the longer axis that can cover every rank is selected, with width winning ties. This policy is cached only through normal kernel shape caches; it is reevaluated for every request.
 
 ### Notes
 
-- The decoder is patched **in place** the first time spatial-shard decode runs and is bound to a single split dimension for the lifetime of the VAE instance.
+- The decoder is patched **in place** the first time spatial-shard decode runs. Its wrappers consult a context-local split dimension and retain an exact direct fallback, allowing later requests to select tile, height, or width safely.
 - Numerical correctness vs. single-GPU decode is covered by `tests/diffusion/distributed/test_wan_spatial_shard.py::test_spatial_shard_decode_matches_reference` (multi-GPU, nightly `full_model` + `distributed_cuda`).
+- QwenImage additionally covers cache discovery, compile compatibility, mixed tile/spatial requests, both axes, and all-rank result broadcast in `tests/diffusion/distributed/test_qwenimage_spatial_shard.py`.
 
 ---
 

docs/design/module/ar_runtime.md

@@ -7,6 +7,7 @@ owners:
   - "@yinpeiqi"
   - "@fake0fan"
   - "@Sy0307"
+  - "@Gaohan123"
 primary_code_paths:
   - vllm_omni/core/**
   - vllm_omni/worker/**

docs/design/module/benchmarking.md

@@ -4,6 +4,7 @@ kind: module
 status: draft
 owners:
   - "@alex-jw-brooks"
+  - "@Bounty-hunter"
 primary_code_paths:
   - vllm_omni/benchmarks/**
   - vllm_omni/entrypoints/cli/benchmark/**

docs/design/module/cache_management.md

@@ -5,6 +5,7 @@ status: draft
 owners:
   - "@Isotr0py"
   - "@princepride"
+  - "@SamitHuang"
 primary_code_paths:
   - vllm_omni/diffusion/cache/**
 related_code_paths:

docs/design/module/diffusion/diffusion_model_integration.md

@@ -3,9 +3,10 @@ title: Diffusion Model Integration
 kind: module
 status: draft
 owners:
-  - "@Isotr0py"
+  - "@fhfuih"
+  - "@Bounty-hunter"
   - "@wtomin"
-  - "@ZJY0516"
+  - "@RuixiangMa"
 primary_code_paths:
   - vllm_omni/diffusion/models/**
   - vllm_omni/diffusion/model_loader/**

docs/design/module/diffusion/diffusion_runtime.md

@@ -6,6 +6,7 @@ owners:
   - "@Isotr0py"
   - "@princepride"
   - "@SamitHuang"
+  - "@fhfuih"
 primary_code_paths:
   - vllm_omni/diffusion/sched/**
   - vllm_omni/diffusion/executor/**

docs/design/module/diffusion/offloader.md

@@ -4,7 +4,8 @@ kind: module
 status: draft
 owners:
   - "@yuanheng-zhao"
-  - "@Isotr0py"
+  - "@david6666666"
+  - "@lishunyang12"
 primary_code_paths:
   - vllm_omni/diffusion/offloader/**
 related_code_paths:

docs/design/module/diffusion/parallelism.md

@@ -6,6 +6,7 @@ owners:
   - "@princepride"
   - "@yuanheng-zhao"
   - "@xuechendi"
+  - "@Bounty-hunter"
 primary_code_paths:
   - vllm_omni/diffusion/distributed/**
   - vllm_omni/diffusion/attention/parallel/**

docs/design/module/entrypoints.md

@@ -6,6 +6,7 @@ architecture_state: current-plus-in-flight
 owners:
   - "@alex-jw-brooks"
   - "@linyueqian"
+  - "@NickCao"
 document_stewards:
   - "@hsliuustc0106"
   - "@Gaohan123"

docs/design/module/execution_platforms.md

@@ -8,8 +8,15 @@ owners:
   - "@xuechendi"
 primary_code_paths:
   - vllm_omni/platforms/**
-related_code_paths:
   - vllm_omni/attention/**
+primary_code_path_owners:
+  # Additional owners scoped to attention kernels (quantized/custom attention)
+  - paths:
+      - vllm_omni/attention/**
+    owners:
+      - "@david6666666"
+      - "@lishunyang12"
+related_code_paths: []
 depends_on:
   - ar_runtime.md
   - diffusion/index.md

docs/design/module/input_output_modality_contracts.md

@@ -6,6 +6,8 @@ architecture_state: current
 owners:
   - "@Sy0307"
   - "@amy-why-3459"
+  - "@Gaohan123"
+  - "@alex-jw-brooks"
 document_stewards:
   - "@hsliuustc0106"
   - "@Gaohan123"

docs/design/module/model_integration.md

@@ -9,6 +9,14 @@ primary_code_paths:
   - vllm_omni/model_executor/**
   - vllm_omni/model_extras/**
   - vllm_omni/plugins/**
+primary_code_path_owners:
+  # Additional owners scoped to a sub-path of model_executor/**
+  - paths:
+      - vllm_omni/model_executor/models/**
+    owners:
+      - "@Sy0307"
+      - "@amy-why-3459"
+      - "@linyueqian"
 related_code_paths:
   - vllm_omni/transformers_utils/**
   - vllm_omni/tokenizers/**

docs/design/module/observability.md

@@ -4,6 +4,7 @@ kind: module
 status: draft
 owners:
   - "@lishunyang12"
+  - "@vraiti"
 primary_code_paths:
   - vllm_omni/metrics/**
 related_code_paths:

docs/mkdocs/hooks/generate_examples.py

@@ -24,6 +24,23 @@ SERVING_MODE_TITLES = {
     "online_serving": "Online serving",
 }
 
+# Keep the Examples navigation focused on reusable modality/task entry points.
+# Model-specific scripts remain available under ``examples/`` and are surfaced
+# from these shared pages instead of getting one page per model.
+GENERAL_EXAMPLE_SLUGS = frozenset(
+    {
+        "image_to_image",
+        "image_to_video",
+        "speech_to_video",
+        "text_to_audio",
+        "text_to_image",
+        "text_to_speech",
+        "text_to_video",
+        "x_to_text",
+        "x_to_video_audio",
+    }
+)
+
 
 def load_model_display_names() -> dict[str, str]:
     try:
@@ -46,6 +63,13 @@ def load_model_display_names() -> dict[str, str]:
 MODEL_DISPLAY_NAMES = load_model_display_names()
 
 
+def is_general_example(example: "Example") -> bool:
+    """Return whether an example should get a generated serving page."""
+    if example.category not in SERVING_MODE_TITLES:
+        return True
+    return example.path.stem in GENERAL_EXAMPLE_SLUGS
+
+
 def fix_case(text: str) -> str:
     subs = {
         "api": "API",
@@ -340,22 +364,21 @@ def update_nav_file(examples: list[Example]):
             examples_by_category[category] = []
         examples_by_category[category].append(example)
 
-    # Build the new Examples section - start with preserved items
+    def category_items(category: str) -> list[dict[str, str]]:
-    examples_section = preserved_items.copy()
+        items = []
-
+        for example in sorted(examples_by_category[category], key=lambda e: e.path.stem):
-    # Add examples grouped by category, sorted by category name
-    for category in sorted(examples_by_category.keys()):
-        category_examples = sorted(examples_by_category[category], key=lambda e: e.path.stem)
-        category_items = []
-        for example in category_examples:
             doc_path = EXAMPLE_DOC_DIR / example.category / f"{example.path.stem}.md"
             rel_path = doc_path.relative_to(ROOT_DIR / "docs")
-            category_items.append({example.nav_title: rel_path.as_posix()})
+            items.append({example.nav_title: rel_path.as_posix()})
+        return items
 
-        if category_items:
+    # Build the new Examples section - start with preserved items.
-            # Format category name (e.g., "offline_inference" -> "Offline Inference")
+    examples_section = preserved_items.copy()
+    for category in sorted(examples_by_category.keys()):
+        items = category_items(category)
+        if items:
             category_title = fix_case(category.replace("_", " ").title())
-            examples_section.append({category_title: category_items})
+            examples_section.append({category_title: items})
 
     # Update the nav structure
     nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section
@@ -390,6 +413,8 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
         for path in category.glob("*/*.md"):
             examples.append(Example(path.parent, category.stem))
 
+    examples = [example for example in examples if is_general_example(example)]
+
     # Generate the example documentation
     for example in sorted(examples, key=lambda e: e.path.stem):
         example_name = f"{example.path.stem}.md"

docs/models/supported_models.md

@@ -17,84 +17,93 @@ th {
 }
 </style>
 
-| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU |
+| Architecture | Models | Example HF Models | NVIDIA GPU | AMD GPU | Ascend NPU | Intel GPU | Recipe |
-|--------------|--------|-------------------|------------|---------|-----|-----------|
+|--------------|--------|-------------------|------------|---------|-----|-----------|--------|
-| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3OmniMoeForConditionalGeneration` | Qwen3-Omni | `Qwen/Qwen3-Omni-30B-A3B-Instruct` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen3-Omni.md) |
-| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen2_5OmniForConditionalGeneration` | Qwen2.5-Omni | `Qwen/Qwen2.5-Omni-7B`, `Qwen/Qwen2.5-Omni-3B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   |
+| `MingFlashOmniForConditionalGeneration` + `MingImagePipeline` | Ming-flash-omni-2.0 (omni-speech + imagegen<sup>1</sup>) | `Jonathan1909/Ming-flash-omni-2.0` | ✅︎ |   |   |   | — |
-| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ |
+| `BagelForConditionalGeneration` | BAGEL (DiT-only) | `ByteDance-Seed/BAGEL-7B-MoT` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | |
+| `InternVLAA1Pipeline` | InternVLA-A1 | `InternRobotics/InternVLA-A1-3B` | ✅︎ | ✅︎ | | | — |
-| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | |
+| `Gr00tN1d7Pipeline` | GR00T N1.7 | `nvidia/GR00T-N1.7-3B` | ✅︎ | | | | — |
-| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `HunyuanImage3ForCausalMM` | HunyuanImage3.0 (DiT-only) | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen-Image) |
-| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImagePipeline` | Qwen-Image-2512 | `Qwen/Qwen-Image-2512` | ✅︎ | | | | [Repository](https://github.com/vllm-project/vllm-omni/blob/main/recipes/Qwen/Qwen-Image-2512.md) |
-| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageLayeredPipeline` | Qwen-Image-Layered | `Qwen/Qwen-Image-Layered` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2511 | `Qwen/Qwen-Image-Edit-2511` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | |
+| `GlmImagePipeline` | GLM-Image | `zai-org/GLM-Image` | ✅︎ | ✅︎ | | | — |
-| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `ZImagePipeline` | Z-Image | `Tongyi-MAI/Z-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | |
+| `Krea2Pipeline` | Krea 2 (Raw + Turbo) | `krea/Krea-2-Raw`, `krea/Krea-2-Turbo` | ✅︎ | | | | — |
-| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `WanPipeline` | Wan2.1-T2V, Wan2.2-T2V, Wan2.2-TI2V | `Wan-AI/Wan2.1-T2V-1.3B-Diffusers`, `Wan-AI/Wan2.1-T2V-14B-Diffusers`, `Wan-AI/Wan2.2-T2V-A14B-Diffusers`, `Wan-AI/Wan2.2-TI2V-5B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `WanImageToVideoPipeline` | Wan2.2-I2V | `Wan-AI/Wan2.2-I2V-A14B-Diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Cosmos3OmniDiffusersPipeline` | Cosmos3 T2I, T2V, I2V, V2V, T2V with sound, action policy | `nvidia/Cosmos3-Nano`, `nvidia/Cosmos3-Super` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22S2VPipeline` | Wan2.2-S2V | `Wan-AI/Wan2.2-S2V-14B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Wan22VACEPipeline` | Wan2.1-VACE | `Wan-AI/Wan2.1-VACE-1.3B-diffusers`, `Wan-AI/Wan2.1-VACE-14B-diffusers` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   |
+| `Wan22VACEPipeline` | Wan2.2-VACE | `Pyros13/Wan2.2-VACE-Fun-A14B-Diffusers` | ✅︎ |   |   |   | — |
-| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | |
+| `LTX2Pipeline` | LTX-2 / LTX-2.3 one-stage T2V and I2V | `Lightricks/LTX-2`, `diffusers/LTX-2.3-Diffusers` | ✅︎ | ✅︎ | | | — |
-| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | |
+| `LTX2DistilledPipeline` | LTX-2 distilled two-stage T2V and I2V | `rootonchair/LTX-2-19b-distilled` | ✅︎ | ✅︎ | | | — |
-| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2I, T2V, TI2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | |
+| `LingBotVideoPipeline` | LingBot-Video dense and MoE T2I, T2V, TI2V | `robbyant/lingbot-video-dense-1.3b`, `robbyant/lingbot-video-moe-30b-a3b` | ✅︎ | | | | — |
-| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | | | |
+| `MiniMaxH3Pipeline` | MiniMax H3 T2VA, first/last-keyframe FL2VA, and mixed-reference Ref2VA | `MiniMaxAI/MiniMax-H3` | ✅︎ | ✅︎ | | | [Published](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3) |
-| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `DreamZeroPipeline` | DreamZero-DROID | `GEAR-Dreams/DreamZero-DROID` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | |
+| `HeliosPipeline`, `HeliosPyramidPipeline` | Helios | `BestWishYsh/Helios-Base`, `BestWishYsh/Helios-Mid`, `BestWishYsh/Helios-Distilled` | ✅︎ | ✅︎ | ✅︎ | | — |
-| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | |
+| `MagiHumanPipeline` | MagiHuman | `SII-GAIR/daVinci-MagiHuman-Base-1080p` | ✅︎ | ✅︎ | | | — |
-| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ |
+| `OvisImagePipeline` | Ovis-Image | `OvisAI/Ovis-Image` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `LongcatImagePipeline` | LongCat-Image | `meituan-longcat/LongCat-Image` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `LongCatImageEditPipeline` | LongCat-Image-Edit | `meituan-longcat/LongCat-Image-Edit` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | |
+| `BooguImagePipeline` | Boogu-Image | `Boogu/Boogu-Image-0.1-Base`, `Boogu/Boogu-Image-0.1-Edit` | ✅︎ | | | | — |
-| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `StableDiffusionXLPipeline` | Stable-Diffusion-XL | `stabilityai/stable-diffusion-xl-base-1.0` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ |
+| `StableDiffusion3Pipeline` | Stable-Diffusion-3 | `stabilityai/stable-diffusion-3.5-medium` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ |
+| `CosyVoice3Model` | CosyVoice3 | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | |
+| `OmniVoiceModel` | OmniVoice | `k2-fsa/OmniVoice` | ✅︎ | | | | — |
-| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | |
+| `VoxCPM2TalkerForConditionalGeneration` | VoxCPM2 | `openbmb/VoxCPM2` | ✅︎ | | | | — |
-| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Preview | `bytedance-research/MammothModa2-Preview` | ✅︎ | ✅︎ | | | — |
-| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | |
+| `MammothModa2ForConditionalGeneration` | MammothModa2-Dev (AR-only image understanding) | `bytedance-research/MammothModa2-Dev` | ✅︎ | | | | — |
-| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Flux2KleinPipeline` | FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B`, `black-forest-labs/FLUX.2-klein-9B` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | |
+| `FluxKontextPipeline` | FLUX.1-Kontext-dev | `black-forest-labs/FLUX.1-Kontext-dev` | ✅︎ | ✅︎ | | | — |
-| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ |
+| `FluxPipeline` | FLUX.1-dev | `black-forest-labs/FLUX.1-dev` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ |
+| `FluxPipeline` | FLUX.1-schnell | `black-forest-labs/FLUX.1-schnell` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ |
+| `OmniGen2Pipeline` | OmniGen2 | `OmniGen2/OmniGen2` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ |
+| `StableAudioPipeline` | Stable-Audio-Open | `stabilityai/stable-audio-open-1.0` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | |
+| `SoulXSingerPipeline` | SoulX-Singer (SVS) | `Soul-AILab/SoulX-Singer` | ✅︎ | | | | — |
-| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | |
+| `SoulXSingerSVCPipeline` | SoulX-Singer-SVC | `Soul-AILab/SoulX-Singer` (`model-svc.pt`) | ✅︎ | | | | — |
-| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | |
+| `AudioXPipeline` | AudioX | `zhangj1an/AudioX` | ✅︎ | ✅︎ | | | — |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-CustomVoice | `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice` | ✅︎ | | | | [Published](https://recipes.vllm.ai/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice) |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-VoiceDesign | `Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `Qwen3TTSForConditionalGeneration` | Qwen3-TTS-12Hz-1.7B-Base | `Qwen/Qwen3-TTS-12Hz-1.7B-Base` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | |
+| `MingTTSForConditionalGeneration` | Ming-omni-tts dense 0.5B | `inclusionAI/Ming-omni-tts-0.5B` | ✅︎ | | | | — |
-| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | |
+| `GLMTTSForConditionalGeneration` | GLM-TTS | `zai-org/GLM-TTS` | ✅︎ | | | | — |
-| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | |
+| `MossTTSNanoForCausalLM` | MOSS-TTS-Nano | `OpenMOSS-Team/MOSS-TTS-Nano` | ✅︎ | | | | — |
-| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | |
+| `MossTTSDelayModel` | MOSS-TTS, MOSS-TTSD, MOSS-SoundEffect, MOSS-VoiceGenerator | `OpenMOSS-Team/MOSS-VoiceGenerator` | ✅︎ | | | | — |
-| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | |
+| `MossTTSRealtime` | MOSS-TTS-Realtime | `OpenMOSS-Team/MOSS-TTS-Realtime` | ✅︎ | | | | — |
-| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | |
+| `HiggsAudioV2ForConditionalGeneration` | Higgs-Audio v2 | `bosonai/higgs-audio-v2-generation-3B-base` | ✅︎ | | | | — |
-| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | |
+| `HiggsMultimodalQwen3ForConditionalGeneration` | Higgs-Audio v3 (TTS) | `bosonai/higgs-audio-v3-tts-4b` | ✅︎ | | | | [Published](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b) |
-| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | |
+| `IndexTTS2TalkerForConditionalGeneration` | IndexTTS-2 | `IndexTeam/IndexTTS-2` | ✅︎ | | | | — |
-| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ |
+| `NextStep11Pipeline` | NextStep-1.1 | `stepfun-ai/NextStep-1.1` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | |
+| `MiMoAudioModel` | MiMo-Audio-7B-Instruct | `XiaomiMiMo/MiMo-Audio-7B-Instruct` | ✅︎ | ✅︎ | | | — |
-| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | |
+| `MiMoV2ASRForCausalLM` | MiMo-V2.5-ASR | `XiaomiMiMo/MiMo-V2.5-ASR` | ✅︎ | ✅︎ | | | — |
-| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | |
+| `Flux2Pipeline` | FLUX.2-dev | `black-forest-labs/FLUX.2-dev` | ✅︎ | ✅︎ | | | — |
-| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ |
+| `FishSpeechSlowARForConditionalGeneration` | Fish Speech S2 Pro | `fishaudio/s2-pro` | ✅︎ | ✅︎ | | ✅︎ | — |
-| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | |
+| `DreamIDOmniPipeline` | DreamID-Omni | `XuGuo699/DreamID-Omni` | ✅︎ | ✅︎ | | | — |
-| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | |
+| `SenseNovaU1Pipeline` | SenseNova-U1 (DiT-only) | `SenseNova/SenseNova-U1-8B-MoT` | ✅︎ | | | | — |
-| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | |
+| `LancePipeline` | Lance | `bytedance-research/Lance` | ✅︎ | | | | — |
-| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | |
+| `HunyuanVideo15Pipeline` | HunyuanVideo-1.5-T2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | ✅︎ | ✅︎ | | | — |
-| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | |
+| `HunyuanVideo15ImageToVideoPipeline` | HunyuanVideo-1.5-I2V | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_i2v`, `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_i2v` | ✅︎ | ✅︎ | | | — |
-| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | |
+| `VoxtralTTSForConditionalGeneration` | Voxtral TTS | `mistralai/Voxtral-4B-TTS-2603` | ✅︎ | ✅︎ | | | — |
-| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | |
+| `CovoAudioForConditionalGeneration` | Covo-Audio-Chat | `tencent/Covo-Audio-Chat` | ✅︎ | | | | — |
-|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | |
+|`DyninOmniForConditionalGeneration` | Dynin-Omni | `snu-aidas/Dynin-Omni` | ✅︎ | | | | — |
-| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | |
+| `MiniCPMO45OmniForConditionalGeneration` | MiniCPM-o 4.5 | `openbmb/MiniCPM-o-4_5` | ✅︎ | | ✅︎ | | — |
-| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ |
+| `ErnieImagePipeline` | ERNIE-Image | `baidu/ERNIE-Image`, `baidu/ERNIE-Image-Turbo` | ✅︎ | ✅︎ | ✅︎ | ✅︎ | — |
-|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | |
+|`HiDreamImagePipeline` | HiDream-I1-Full | `HiDream-ai/HiDream-I1-Full` | ✅︎ | ✅︎ | | | — |
+
+The `Recipe` column links the corresponding deployment recipe. `Published` is
+preferred when a corresponding `recipes.vllm.ai` page exists; otherwise the
+link points to the repository recipe. `—` means that no recipe link has been
+added for that model row yet.
+
+For rows with an audited recipe link, the hardware checkmarks reflect hardware
+explicitly documented in that recipe. Other rows retain the implementation
+support metadata until their recipe is audited.
 
 ✅︎ indicates the model is supported on that backend. Empty cells mean not listed as supported on that backend.
 

docs/user_guide/diffusion/attention_backends.md

@@ -283,23 +283,20 @@ blocks — use Ulysses SP (`ring_degree=1`).
 
 ### Which geometries run sparse
 
-Sparsity is only applied when the video segment is a **multiple of 128 rows**, where the row count
+MindIE-SD rf_v2 handles arbitrary video grids by spatially rearranging video first and, when
-is `latent_t × (height / 32) × (width / 32)`. Otherwise `rf_v2`'s block mask and the kernel's own
+necessary, promoting a real-video suffix to its always-kept prefix segment. It never pads: rf_v2
-tiling disagree on the block count, and the block straddling the seam mixes video and prefix rows
+does not consume an attention mask for padded keys. The remaining video rows stay sparse, while the
-that selection may then drop. Any resolution still runs — an unaligned geometry falls back to dense
+promoted rows remain visible to every query and key.
-attention and logs `RAINFUSION_ATTN staying dense` with the row count it computed — but it gets no
-speedup, so pick an aligned geometry when you want one.
 
-Alignment is necessary, not sufficient, for good quality. `rf_v2` groups video positions into 8x8
+For example, MiniMax-H3 at 1344x768 has grid `(62, 24, 42)`: its 62496 video rows leave a 32-row
-spatial tiles (two tiles fill one 128-row block), which is what makes a selected block a compact
+128-block residue, and its two non-8-wide latent columns form a 2928-row rearranged suffix.
-patch of the frame. When the latent `h` or `w` is not a multiple of 8, the leftover rows or columns
+MindIE-SD promotes 2976 rows, leaving 59520 sparse rows (`465 × 128`). This keeps the block mask
-are peeled off and appended as a flat run instead of being tiled, so they get pooled with spatially
+and kernel tiling aligned, at the cost of retaining more blocks.
-distant positions and selection can no longer rank them meaningfully. This is silent, and invisible
-to a `sparsity=0` check, because a fully populated mask does not care how blocks are grouped.
 
-"Multiple of 8" on the latent grid means **width and height that are multiples of 256**. Aligned
+8x8-aligned spatial grids remain preferable for performance. A latent `h` or `w` not divisible by 8
-resolutions off that grid still run sparse; they just lose more fidelity at the same `sparsity`,
+creates an always-kept residual suffix and lowers realized sparsity. "Multiple of 8" on the latent
-which you can buy back with `start_step`.
+grid means **width and height that are multiples of 256**. This path requires a MindIE-SD release
+that implements protected video tails for rf_v2.
 
 ## End-to-End Benchmark (BF16, sm_120 RTX Pro 6000 Blackwell)
 

docs/user_guide/diffusion/parallelism/vae_parallelism.md

@@ -15,7 +15,7 @@
 
 ## Overview
 
-VAE parallelism distributes VAE (Variational AutoEncoder) decode/encode work across multiple GPUs. This guide covers VAE patch/tile parallelism, which splits latent space into spatial tiles or patches, and Wan spatial-shard decode, which shards decoder feature maps along height or width.
+VAE parallelism distributes VAE (Variational AutoEncoder) decode/encode work across multiple GPUs. This guide covers VAE patch/tile parallelism, which splits latent space into spatial tiles or patches, and Wan/QwenImage spatial-shard decode, which shards decoder feature maps along height or width.
 
 This is particularly useful for:
 - **High-resolution image generation** where VAE decode can become a memory bottleneck
@@ -113,7 +113,7 @@ In `DiffusionParallelConfig`:
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
 | `vae_patch_parallel_size` | int | 1 | Number of GPUs for VAE patch/tile parallelism. Set to 2 or higher to enable. Should typically match `tensor_parallel_size` as they share the same process group. |
-| `vae_parallel_mode` | str | `"tile"` | VAE parallel decode strategy: `"tile"` (default tile/patch parallel decode), `"spatial_shard_height"`, or `"spatial_shard_width"` (spatially-sharded decode, Wan only). See [Spatially-Sharded Decode](#spatially-sharded-decode-wan). |
+| `vae_parallel_mode` | str | `"auto"` | VAE parallel decode strategy: `"auto"` (shape/model/topology-aware selection), `"tile"`, `"spatial_shard_height"`, or `"spatial_shard_width"`. Spatial sharding supports Wan and the distributed QwenImage backend. See [Spatially-Sharded Decode](#spatially-sharded-decode-wan-and-qwenimage). |
 
 Additional requirements:
 
@@ -126,9 +126,9 @@ Additional requirements:
 
 ---
 
-## Spatially-Sharded Decode (Wan)
+## Spatially-Sharded Decode (Wan and QwenImage)
 
-The default `vae_parallel_mode="tile"` distributes whole tiles across ranks. For the **Wan** VAE there is an alternative decode strategy, **spatially-sharded decode**, selected via `vae_parallel_mode="spatial_shard_height"` or `vae_parallel_mode="spatial_shard_width"`.
+The default `vae_parallel_mode="auto"` selects spatial-shard decode only after a Wan or distributed QwenImage request is already large enough to enter Diffusers' tiled-decode path and the VAE uses the full DiT decode group. It splits the longer eligible spatial axis to reduce halo traffic. Direct-decode requests, partial groups, and other VAE families keep their existing path. Set `vae_parallel_mode="tile"` to force the previous behavior, or `"spatial_shard_height"` / `"spatial_shard_width"` to force an axis.
 
 Instead of assigning independent tiles to ranks, spatial-shard decode shards the decoder feature maps along the height (`spatial_shard_height`) or width (`spatial_shard_width`) dimension and exchanges halo rows/columns between neighboring ranks around the spatial convolutions. This keeps the receptive field correct across shard boundaries, so the result matches the single-GPU decode within numerical tolerance.
 
@@ -141,7 +141,7 @@ omni = Omni(
     parallel_config=DiffusionParallelConfig(
         tensor_parallel_size=2,
         vae_patch_parallel_size=2,               # must match the DiT group size
-        vae_parallel_mode="spatial_shard_width", # or "spatial_shard_height"
+        vae_parallel_mode="auto",                # default
     ),
 )
 ```
@@ -152,14 +152,18 @@ Or from the CLI / serving entrypoint:
 vllm serve Wan-AI/Wan2.1-T2V-1.3B-Diffusers --omni \
     --tensor-parallel-size 2 \
     --vae-patch-parallel-size 2 \
-    --vae-parallel-mode spatial_shard_width
+    --vae-parallel-mode auto
 ```
 
 **Constraints and behavior:**
 
-- Spatial-shard decode is **decode-only** and currently implemented for the **Wan** VAE. Other models ignore `spatial_shard_*` modes.
+- Spatial-shard decode is **decode-only** and implemented for the **Wan** VAE and the distributed **QwenImage** backend used by Qwen-Image and Krea2. Pipelines using a different VAE backend keep their existing behavior.
-- It requires `vae_patch_parallel_size` to **match the DiT process group size**. If it does not, the VAE logs a warning and **falls back to tile-parallel decode** at runtime.
+- It requires `vae_patch_parallel_size` to **match the DiT process group size**. `auto` quietly falls back to tile decode for a partial group; an explicitly forced spatial mode logs a warning.
-- `spatial_shard_height` and `spatial_shard_width` are mutually exclusive for a given VAE instance (the decoder is patched in place for a single split dimension).
+- The decoder's context-aware wrappers retain the direct path, so one process can alternate small/large and portrait/landscape requests safely.
+- Wan preserves its rank-0-only decode result, while QwenImage preserves its existing all-rank result by broadcasting after rank-0 assembly.
+- Spatial sharding trades activation memory for latency as resolution grows. Use `vae_parallel_mode="tile"` when bounded VAE memory is more important than decode speed.
+
+The automatic policy is adapted from [SGLang #28071](https://github.com/sgl-project/sglang/pull/28071) and narrowed to vLLM-Omni's parity-tested Wan and QwenImage backends.
 
 For end-to-end latency/throughput, launch serving with the desired `vae_parallel_mode` and use the existing diffusion serving benchmark:
 

docs/user_guide/examples/online_serving/diffusers_pipeline_adapter.md

@@ -99,7 +99,7 @@ a native vLLM-Omni pipeline for those cases.
 ### Attention Backends
 
 The diffusers backend converts
-[vLLM-Omni standard of attention backend setting](../../../docs/user_guide/diffusion/attention_backends.md)
+[vLLM-Omni standard of attention backend setting](../../diffusion/attention_backends.md)
 to [diffusers standard](https://huggingface.co/docs/diffusers/optimization/attention_backends#available-backends).
 
 Specifically for `FLASH_ATTN`, it will first attempt to use FlashAttention-3 and then FlashAttention-2.

examples/quantization/check_modelopt_fp8_export.py

@@ -1,247 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Verify a ModelOpt FP8 diffusers checkpoint exported by
-quantize_wan2_2_modelopt_fp8.py / quantize_hunyuanvideo_15_modelopt_fp8.py.
-
-Three checks:
-  A. transformer/config.json has a sane quantization_config block.
-  B. transformer/*.safetensors contains FP8 (float8_e4m3fn) quantized tensors.
-  C. transformer disk size is materially smaller than a BF16 baseline.
-
-Example:
-    python examples/quantization/check_modelopt_fp8_export.py \\
-        --output ./hv15-480p-modelopt-fp8
-
-    # Optional: compare disk size against a local or HF BF16 baseline.
-    python examples/quantization/check_modelopt_fp8_export.py \\
-        --output ./hv15-480p-modelopt-fp8 \\
-        --baseline hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v
-"""
-
-from __future__ import annotations
-
-import argparse
-import json
-import sys
-from collections import Counter
-from pathlib import Path
-
-SUPPORTED_ALGOS = ("FP8",)
-
-
-def _check_config(transformer_dir: Path) -> tuple[int, str | None]:
-    """Returns (status, quant_algo). status: 0 pass, 1 fail, 2 warn."""
-    cfg_path = transformer_dir / "config.json"
-    if not cfg_path.exists():
-        print(f"[FAIL] {cfg_path} missing.")
-        return 1, None
-
-    with cfg_path.open(encoding="utf-8") as f:
-        cfg = json.load(f)
-
-    qc = cfg.get("quantization_config")
-    if not isinstance(qc, dict):
-        print(f"[FAIL] No `quantization_config` block in {cfg_path}.")
-        return 1, None
-
-    print(f"[A] quantization_config from {cfg_path}:")
-    print(json.dumps(qc, indent=2))
-
-    quant_algo = qc.get("quant_algo")
-    issues = []
-    if qc.get("quant_method") != "modelopt":
-        issues.append(f"quant_method={qc.get('quant_method')!r} (expected 'modelopt')")
-    if quant_algo not in SUPPORTED_ALGOS:
-        issues.append(
-            f"quant_algo={quant_algo!r} (expected one of {SUPPORTED_ALGOS} — vllm-omni adapter may not auto-detect)"
-        )
-
-    if issues:
-        print("[A] WARN — config looks incomplete:")
-        for issue in issues:
-            print(f"    - {issue}")
-        return 2, quant_algo
-    print(f"[A] PASS — config looks correct (quant_algo={quant_algo}).")
-    return 0, quant_algo
-
-
-def _read_safetensors_header(path: Path) -> dict:
-    """Read the JSON header of a safetensors file. Bypass-safe — doesn't materialize tensors.
-
-    Returns {tensor_name: {'dtype': 'F8_E4M3', 'shape': [...], 'data_offsets': [...]}}.
-    Header dtype strings: F8_E4M3, F8_E5M2, BF16, F16, F32, F64, I8, I16, I32, I64, BOOL, U8, ...
-    """
-    import struct
-
-    with open(path, "rb") as f:
-        header_len = struct.unpack("<Q", f.read(8))[0]
-        header = json.loads(f.read(header_len))
-    header.pop("__metadata__", None)
-    return header
-
-
-def _classify_weight_scale_granularity(weight_scale_shapes: list[list[int]]) -> str:
-    """Infer per-tensor vs per-channel vs per-block from sample weight_scale shapes.
-
-    ModelOpt block-wise produces shapes like `[16, 1, 16, 1]` (broadcasting dims of 1
-    interleaved with block-count dims). We count "meaningful" dims — ones with size > 1 —
-    and classify: 0 meaningful dims = per-tensor (scalar), 1 = per-channel, 2+ = per-block.
-    """
-    if not weight_scale_shapes:
-        return "no weight_scale tensors found"
-
-    def meaningful_dims(shape: list[int]) -> int:
-        return sum(1 for d in shape if d > 1)
-
-    per_tensor = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 0)
-    per_channel = sum(1 for s in weight_scale_shapes if meaningful_dims(s) == 1)
-    per_block = sum(1 for s in weight_scale_shapes if meaningful_dims(s) >= 2)
-    total = len(weight_scale_shapes)
-    if per_tensor == total:
-        return "per-tensor (all scalar scales)"
-    if per_channel == total:
-        return "per-channel (1 meaningful dim)"
-    if per_block == total:
-        return "per-block (2+ meaningful dims — e.g. [M//bm, 1, N//bn, 1] for tiles)"
-    return f"mixed: per-tensor={per_tensor}, per-channel={per_channel}, per-block={per_block} of {total}"
-
-
-def _check_safetensors(transformer_dir: Path) -> int:
-    """Returns 0 on pass, 1 on fail. Reads on-disk dtype from the safetensors header."""
-    files = sorted(transformer_dir.glob("*.safetensors"))
-    if not files:
-        print(f"[FAIL] No *.safetensors in {transformer_dir}.")
-        return 1
-
-    header_dtype_counts: Counter[str] = Counter()
-    sample_quant_weight_keys: list[str] = []
-    sample_scale_keys: list[str] = []
-    weight_scale_shapes: list[list[int]] = []
-    sample_weight_scale_entries: list[tuple[str, list[int]]] = []
-
-    for f in files:
-        try:
-            header = _read_safetensors_header(f)
-        except Exception as exc:
-            print(f"[B] WARN — could not parse header of {f}: {exc}")
-            continue
-        for k, info in header.items():
-            dtype = info.get("dtype", "?")
-            header_dtype_counts[dtype] += 1
-            # FP8 stores weights as F8_E4M3 directly.
-            if dtype.startswith("F8") and k.endswith(".weight") and len(sample_quant_weight_keys) < 5:
-                sample_quant_weight_keys.append(k)
-            if k.endswith(("_scale", ".weight_scale", ".input_scale", "_scale_inv")) and len(sample_scale_keys) < 5:
-                sample_scale_keys.append(k)
-            if k.endswith(".weight_scale"):
-                weight_scale_shapes.append(info.get("shape", []))
-                if len(sample_weight_scale_entries) < 5:
-                    sample_weight_scale_entries.append((k, info.get("shape", [])))
-
-    print(f"\n[B] On-disk dtype counts across {len(files)} safetensors file(s) (from header, not get_tensor):")
-    for dtype, count in sorted(header_dtype_counts.items(), key=lambda kv: -kv[1]):
-        marker = "  <-- FP8" if dtype.startswith("F8") else ""
-        print(f"    {dtype:10s} {count:>6d}{marker}")
-
-    quant_count = sum(c for d, c in header_dtype_counts.items() if d.startswith("F8"))
-    if quant_count == 0:
-        print("[B] FAIL — no FP8 tensors on disk. Calibration likely did not actually quantize the weights.")
-        return 1
-
-    print(f"[B] PASS — {quant_count} FP8 tensors stored on disk.")
-    if sample_quant_weight_keys:
-        print(f"    sample quantized weight tensors: {sample_quant_weight_keys[:3]}")
-    if sample_scale_keys:
-        print(f"    sample scale tensors:            {sample_scale_keys[:3]}")
-    print("    (Note: torch's get_tensor() may return these as bf16 views on some versions —")
-    print("     irrelevant; vLLM's loader uses native FP8 ops.)")
-
-    # Weight-scale granularity — per-tensor (scalar) vs per-channel (1-D) vs per-block (N-D).
-    print(f"\n    weight_scale granularity: {_classify_weight_scale_granularity(weight_scale_shapes)}")
-    for key, shape in sample_weight_scale_entries[:3]:
-        print(f"      {key}: shape {shape}")
-    return 0
-
-
-def _disk_size_gib(p: Path) -> float:
-    return sum(f.stat().st_size for f in p.rglob("*") if f.is_file()) / (1024**3)
-
-
-def _check_size_vs_baseline(transformer_dir: Path, baseline: str | None) -> int:
-    """Returns 0 always (informational only)."""
-    quant_size = _disk_size_gib(transformer_dir)
-    print(f"\n[C] FP8 transformer disk size: {quant_size:.2f} GiB")
-
-    if baseline is None:
-        print("[C] SKIP — pass --baseline <path or HF id> to compare against BF16.")
-        return 0
-
-    baseline_path = Path(baseline)
-    if not baseline_path.exists():
-        # Try HF download.
-        try:
-            from huggingface_hub import snapshot_download
-        except ImportError:
-            print("[C] SKIP — huggingface_hub not installed and baseline not a local path.")
-            return 0
-        print(f"    Downloading baseline transformer from HF: {baseline}")
-        baseline_path = Path(snapshot_download(baseline, allow_patterns=["transformer/*"]))
-
-    bf16_dir = baseline_path / "transformer" if (baseline_path / "transformer").exists() else baseline_path
-    bf16_size = _disk_size_gib(bf16_dir)
-    if bf16_size == 0:
-        print(f"[C] WARN — baseline transformer dir empty: {bf16_dir}")
-        return 0
-
-    # Expected reduction for FP8: ~50%.
-    min_reduction = 30
-    reduction = (1 - quant_size / bf16_size) * 100
-    print(f"[C] BF16 baseline transformer disk size: {bf16_size:.2f} GiB ({bf16_dir})")
-    print(f"[C] Disk reduction: {reduction:.1f}%  (FP8 transformer is {quant_size / bf16_size:.0%} of BF16)")
-    if reduction < min_reduction:
-        print(
-            f"[C] WARN — FP8 should typically reduce disk by ~40-50%; <{min_reduction}% suggests partial quantization."
-        )
-    return 0
-
-
-def main() -> None:
-    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
-    p.add_argument("--output", required=True, help="Path to the exported ModelOpt FP8 checkpoint root.")
-    p.add_argument(
-        "--baseline",
-        default=None,
-        help="Optional BF16 baseline (local diffusers dir or HF id) for disk-size comparison.",
-    )
-    args = p.parse_args()
-
-    out_root = Path(args.output).expanduser().resolve()
-    transformer_dir = out_root / "transformer"
-    if not transformer_dir.exists():
-        print(f"[FAIL] {transformer_dir} does not exist.")
-        sys.exit(1)
-
-    print(f"Checking: {out_root}\n")
-
-    fail = 0
-    config_status, _quant_algo = _check_config(transformer_dir)
-    fail |= config_status
-    fail |= _check_safetensors(transformer_dir)
-    _check_size_vs_baseline(transformer_dir, args.baseline)
-
-    print()
-    if fail == 0:
-        print("=" * 60)
-        print("ALL CHECKS PASSED — checkpoint looks ready for vllm-omni serving.")
-    elif fail == 1:
-        print("=" * 60)
-        print("FAILURES detected — calibration may need to be re-run.")
-        sys.exit(1)
-    else:
-        print("=" * 60)
-        print("WARNINGS only — checkpoint may serve but with caveats. See [A] above.")
-
-
-if __name__ == "__main__":
-    main()

examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py

@@ -1,448 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Quantize HunyuanVideo-1.5 (480p T2V) to a ModelOpt FP8 Hugging Face checkpoint.
-
-Calibrates the DiT transformer using a small video prompt set and exports a
-diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
-The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
-(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
-
-Layers kept full precision match the #2728 / #2795 pattern: modulation,
-AdaLayerNorm, entry/exit projections, embeddings, the token refiner path,
-and final proj_out. MHA quantizers are off by default; HV-1.5 self-attention
-empirically degrades under FP8 (see #2920 ablation).
-
-Example:
-    python examples/quantization/quantize_hunyuanvideo_15_modelopt_fp8.py \\
-        --model hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v \\
-        --output ./hv15-480p-modelopt-fp8 \\
-        --overwrite
-"""
-
-from __future__ import annotations
-
-import argparse
-import copy
-import json
-import re
-import shutil
-import sys
-from pathlib import Path
-from typing import Any
-
-import torch
-from diffusers import DiffusionPipeline
-
-DEFAULT_PROMPTS = [
-    "A dog running across a field of golden wheat.",
-    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
-    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
-    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
-    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
-    "A close-up of a blooming rose covered in morning dew, soft natural light.",
-    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
-    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
-]
-
-
-def _build_parser() -> argparse.ArgumentParser:
-    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
-    p.add_argument("--model", required=True, help="Input HV-1.5 diffusers directory or HF id.")
-    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
-    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
-    p.add_argument("--height", type=int, default=480)
-    p.add_argument("--width", type=int, default=832)
-    p.add_argument(
-        "--num-frames",
-        type=int,
-        default=33,
-        help="Frames per calibration sample. 33 matches the typical short benchmark.",
-    )
-    p.add_argument("--guidance-scale", type=float, default=6.0)
-    p.add_argument(
-        "--calib-steps",
-        type=int,
-        default=10,
-        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
-    )
-    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
-    p.add_argument("--seed", type=int, default=42)
-    p.add_argument(
-        "--prompt",
-        action="append",
-        default=[],
-        help="Custom calibration prompt. Repeat to provide multiple.",
-    )
-    p.add_argument(
-        "--quantize-mha",
-        action="store_true",
-        help="Enable FP8 attention K/V/softmax quantizers. Off by default — empirically degrades HV-1.5 video output.",
-    )
-    p.add_argument(
-        "--weight-block-size",
-        type=str,
-        default=None,
-        help="Per-block weight quantization as 'M,N' (e.g. '128,128' for 128x128 tiles). "
-        "Default: per-tensor (one scale per linear). Block-wise typically gives tighter quality at "
-        "negligible memory cost. Static FP8 is exempt from upstream vLLM's online block-wise gate.",
-    )
-    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
-    return p
-
-
-def _parse_block_size(spec: str | None) -> list[int] | None:
-    if spec is None:
-        return None
-    parts = [int(x) for x in spec.split(",") if x.strip()]
-    if len(parts) != 2:
-        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
-    return parts
-
-
-def _require_modelopt() -> Any:
-    try:
-        import modelopt.torch.quantization as mtq
-    except ModuleNotFoundError as exc:
-        raise SystemExit(
-            "NVIDIA ModelOpt is not installed. Install with:\n"
-            "  pip install 'nvidia-modelopt[all]'\n"
-            f"Original error: {exc}"
-        ) from exc
-    return mtq
-
-
-def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
-    model_path = args.model
-    output_dir = Path(args.output).expanduser().resolve()
-    if output_dir.exists():
-        if not args.overwrite:
-            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
-        shutil.rmtree(output_dir)
-    return model_path, output_dir
-
-
-def _select_dtype(name: str) -> torch.dtype:
-    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
-
-
-def _build_prompts(args: argparse.Namespace) -> list[str]:
-    prompts = args.prompt or DEFAULT_PROMPTS
-    if args.calib_size <= 0:
-        raise SystemExit("--calib-size must be positive.")
-    if len(prompts) < args.calib_size:
-        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
-        prompts = (prompts * repeats)[: args.calib_size]
-    return prompts[: args.calib_size]
-
-
-# Layers to KEEP at full precision (mirror of the #2920 wiring + #2728/#2795 skip pattern).
-# - x_embedder, image_embedder, context_embedder*, time_embed*, cond_type_embed: entry/embedding
-# - norm_out, norm1*.linear, norm1_context*.linear, norm2*, norm2_context*: AdaLayerNorm modulation
-# - proj_out: final output projection
-# - token_refiner*: text-encoder refinement uses diffusers raw nn.Linear
-def _filter_func_hv15(name: str) -> bool:
-    pattern = re.compile(
-        r"(proj_out.*|"
-        r".*(x_embedder|image_embedder|context_embedder|context_embedder_2|"
-        r"time_embed|cond_type_embed|"
-        r"norm_out|norm1\.linear|norm1_context\.linear|norm2|norm2_context|"
-        r"token_refiner).*)"
-    )
-    return pattern.match(name) is not None
-
-
-def _mha_filter_func(name: str) -> bool:
-    pattern = re.compile(
-        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
-    )
-    return pattern.match(name) is not None
-
-
-def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
-    if not hasattr(mtq, "disable_quantizer"):
-        return
-    mtq.disable_quantizer(backbone, _filter_func_hv15)
-    if not quantize_mha:
-        mtq.disable_quantizer(backbone, _mha_filter_func)
-
-
-def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
-    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
-    if hasattr(pipe, "set_progress_bar_config"):
-        pipe.set_progress_bar_config(disable=True)
-    pipe.to("cuda")
-    return pipe
-
-
-def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
-    generator = torch.Generator(device="cuda")
-
-    # Try to set guidance on the pipeline's guider object up front (modern
-    # diffusers HV-1.5 uses a Guider abstraction, not a per-call kwarg). Falls
-    # back silently — calibration uses whatever default the pipeline ships with.
-    guider = getattr(pipe, "guider", None)
-    if guider is not None and hasattr(guider, "guidance_scale"):
-        try:
-            guider.guidance_scale = args.guidance_scale
-        except Exception:
-            pass
-
-    base_kwargs = dict(
-        height=args.height,
-        width=args.width,
-        num_frames=args.num_frames,
-        num_inference_steps=args.calib_steps,
-        output_type="latent",
-    )
-
-    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
-        with torch.inference_mode():
-            for idx, prompt in enumerate(prompts):
-                generator.manual_seed(args.seed + idx)
-                # Try with guidance_scale first; fall back without on TypeError
-                # for pipelines (like HV-1.5) that take CFG via guider config.
-                try:
-                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
-                except TypeError as exc:
-                    if "guidance_scale" not in str(exc):
-                        raise
-                    pipe(prompt=prompt, generator=generator, **base_kwargs)
-
-    return forward_loop
-
-
-def _summarize_export(output_dir: Path) -> None:
-    cfg_path = output_dir / "transformer" / "config.json"
-    if not cfg_path.exists():
-        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
-        return
-    with cfg_path.open(encoding="utf-8") as f:
-        cfg = json.load(f)
-    qc = cfg.get("quantization_config")
-    if not isinstance(qc, dict):
-        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
-        return
-    print("Export summary:")
-    print(f"  quant_method: {qc.get('quant_method')}")
-    print(f"  quant_algo:   {qc.get('quant_algo')}")
-    producer = qc.get("producer")
-    if isinstance(producer, dict):
-        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
-    print(f"  config path:  {cfg_path}")
-
-
-def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
-    """Convert in-memory weights of quantized modules to actual FP8 storage.
-
-    `export_hf_checkpoint` skips this step for unknown model types (HV-1.5 isn't
-    in ModelOpt's recognized-model registry), so we must call the per-weight
-    export helper ourselves. Same workaround as the HunyuanImage-3 calibration
-    helper.
-    """
-    from modelopt.torch.export.quant_utils import (
-        QUANTIZATION_NONE,
-        get_quantization_format,
-        quantizer_attr_names,
-        weight_attr_names,
-    )
-    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
-
-    exported = 0
-    for name, module in backbone.named_modules():
-        try:
-            quantization_format = get_quantization_format(module)
-        except Exception as exc:
-            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
-            continue
-        if quantization_format == QUANTIZATION_NONE:
-            continue
-        for weight_name in weight_attr_names(module):
-            quantizer_attrs = quantizer_attr_names(weight_name)
-            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
-            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
-                continue
-            _export_quantized_weight(module, dtype, weight_name)
-            exported += 1
-    return exported
-
-
-def _hv15_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
-    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913).
-
-    Same shape as the HunyuanImage-3 author's _hunyuan_quant_config(). When
-    `weight_block_size` is given, advertise block-wise weight quantization in
-    the saved metadata (so consumers know to expect multi-element scale tensors).
-    """
-    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
-    if weight_block_size is not None:
-        weights_cfg["strategy"] = "block"
-        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
-    return {
-        "config_groups": {
-            "group_0": {
-                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
-                "weights": weights_cfg,
-                "targets": ["Linear"],
-            }
-        },
-        "ignore": [
-            "context_embedder*",
-            "context_embedder_2*",
-            "cond_type_embed*",
-            "image_embedder*",
-            "norm1.linear*",
-            "norm1_context.linear*",
-            "norm2*",
-            "norm2_context*",
-            "norm_out*",
-            "proj_out*",
-            "time_embed*",
-            "token_refiner*",
-            "x_embedder*",
-        ],
-        "producer": {"name": "modelopt"},
-        "quant_algo": "FP8",
-        "quant_method": "modelopt",
-    }
-
-
-def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
-    """Inject quant_algo: FP8 + config_groups into transformer/config.json so
-    vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8."""
-    cfg_path = output_dir / "transformer" / "config.json"
-    with cfg_path.open(encoding="utf-8") as f:
-        cfg = json.load(f)
-
-    new_qc = _hv15_quant_config_block(weight_block_size=weight_block_size)
-    existing = cfg.get("quantization_config")
-    if isinstance(existing, dict):
-        producer = existing.get("producer")
-        if isinstance(producer, dict):
-            new_qc["producer"] = producer
-
-    cfg["quantization_config"] = new_qc
-    with cfg_path.open("w", encoding="utf-8") as f:
-        json.dump(cfg, f, indent=2)
-
-
-def _save_pipeline_with_fp8_transformer(
-    pipe: DiffusionPipeline,
-    model_path: str,
-    output_dir: Path,
-    max_shard_size: str = "5GB",
-) -> None:
-    """Save the pipeline with the (now FP8) transformer.
-
-    Copies the source directory verbatim except for `transformer/`, then
-    saves the transformer with quantizers hidden so the state dict contains
-    only the FP8 weights + scale tensors.
-    """
-    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
-
-    src = Path(model_path)
-    if not src.exists():
-        from huggingface_hub import snapshot_download
-
-        src = Path(snapshot_download(model_path))
-
-    if output_dir.exists():
-        shutil.rmtree(output_dir)
-    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer"))
-
-    transformer_out = output_dir / "transformer"
-    # `hide_quantizers_from_state_dict` walks named_modules(); pass the actual
-    # nn.Module (transformer), not the diffusers Pipeline wrapper.
-    with hide_quantizers_from_state_dict(pipe.transformer):
-        pipe.transformer.save_pretrained(
-            str(transformer_out),
-            safe_serialization=True,
-            max_shard_size=max_shard_size,
-        )
-
-
-def main() -> None:
-    args = _build_parser().parse_args()
-    if not torch.cuda.is_available():
-        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
-
-    mtq = _require_modelopt()
-    model_path, output_dir = _ensure_paths(args)
-    dtype = _select_dtype(args.dtype)
-    prompts = _build_prompts(args)
-
-    print("Quantization plan:")
-    weight_block_size = _parse_block_size(args.weight_block_size)
-
-    print(f"  input:           {args.model}")
-    print(f"  output:          {output_dir}")
-    print(f"  dtype:           {dtype}")
-    print(f"  height/width:    {args.height}x{args.width}")
-    print(f"  num_frames:      {args.num_frames}")
-    print(f"  calib_size:      {len(prompts)}")
-    print(f"  calib_steps:     {args.calib_steps}")
-    print(f"  quantize_mha:    {args.quantize_mha}")
-    print(
-        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
-    )
-
-    pipe = _load_pipeline(model_path, dtype)
-    backbone = pipe.transformer
-
-    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
-    if weight_block_size is not None:
-        # Switch from per-tensor (default) to block-wise weight quantization.
-        # ModelOpt's wildcard "*weight_quantizer" matches every linear's weight quantizer.
-        quant_config["quant_cfg"]["*weight_quantizer"] = {
-            "num_bits": (4, 3),  # E4M3 (FP8 weights, same as default)
-            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
-        }
-        print(
-            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
-            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
-        )
-
-    forward_loop = _build_forward_loop(pipe, args, prompts)
-    quantized = mtq.quantize(backbone, quant_config, forward_loop)
-    if quantized is not None:
-        pipe.transformer = quantized
-        backbone = quantized
-
-    _disable_known_problematic_quantizers(mtq, backbone, quantize_mha=args.quantize_mha)
-
-    print("\nForcing FP8 weight serialization (HV-1.5 isn't in ModelOpt's recognized-model registry,")
-    print("so we have to call the per-weight export helper ourselves)...")
-    exported = _force_export_quantized_weights(backbone, dtype)
-    print(f"  -> {exported} weights converted to FP8 in memory")
-    if exported == 0:
-        raise SystemExit(
-            "No quantized weights were exported. Calibration may have skipped every layer "
-            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
-            "weight quantizers."
-        )
-
-    print("\nSaving pipeline with FP8 transformer...")
-    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
-    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
-    print(f"Saved to: {output_dir}")
-    _summarize_export(output_dir)
-
-    print("\nNext: validate the checkpoint with vllm-omni:")
-    print(
-        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
-        f"    --model {output_dir} \\\n"
-        "    --quantization fp8 \\\n"
-        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
-        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
-        "    --num-inference-steps 30 --guidance-scale 6.0 --seed 42 \\\n"
-        "    --output outputs/hv15_modelopt_fp8.mp4 \\\n"
-        "    --enforce-eager"
-    )
-    print(
-        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
-        "checkpoint's config.json has modelopt metadata.)"
-    )
-
-
-if __name__ == "__main__":
-    main()

examples/quantization/quantize_wan2_2_modelopt_fp8.py

@@ -1,471 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-"""Quantize Wan2.2 (TI2V-5B, 704x1280 T2V) to a ModelOpt FP8 Hugging Face checkpoint.
-
-Calibrates the DiT transformer using a small video prompt set and exports a
-diffusers-style directory whose transformer carries ModelOpt FP8 metadata.
-The exported checkpoint is consumable by vllm-omni's ModelOpt FP8 adapter
-(see vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py).
-
-Layers kept full precision match the #2728 / #2795 pattern: condition embedder
-(time/text/image), patch embedding, modulation (scale_shift_table), final
-norm + proj_out, and sequence-parallel helpers. All attention + FFN linears
-are quantized — static calibration handles the numerics that online FP8
-couldn't (see #2920 ablation).
-
-Default target is `Wan-AI/Wan2.2-TI2V-5B-Diffusers`, the dense 5B variant that
-fits 80GB BF16. The A14B MoE variants need 2+ GPUs and are out of scope here.
-
-Example:
-    python examples/quantization/quantize_wan2_2_modelopt_fp8.py \\
-        --model Wan-AI/Wan2.2-TI2V-5B-Diffusers \\
-        --output ./wan22-ti2v-modelopt-fp8 \\
-        --overwrite
-"""
-
-from __future__ import annotations
-
-import argparse
-import copy
-import json
-import re
-import shutil
-import sys
-from pathlib import Path
-from typing import Any
-
-import torch
-from diffusers import DiffusionPipeline
-
-DEFAULT_PROMPTS = [
-    "A dog running across a field of golden wheat.",
-    "An astronaut riding a horse across the surface of Mars, red dust swirling, cinematic wide shot.",
-    "A hummingbird hovering in front of a vibrant red flower, slow motion, macro shot.",
-    "A crackling campfire at night under a starry sky, sparks rising into the dark.",
-    "An underwater shot of a coral reef with tropical fish swimming by, sun rays piercing the water.",
-    "A close-up of a blooming rose covered in morning dew, soft natural light.",
-    "A peaceful mountain village at dawn, mist rolling over the rooftops, cinematic establishing shot.",
-    "A skateboarder doing a kickflip in an urban plaza, slow motion, golden hour lighting.",
-]
-
-
-def _build_parser() -> argparse.ArgumentParser:
-    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
-    p.add_argument("--model", required=True, help="Input Wan2.2 diffusers directory or HF id.")
-    p.add_argument("--output", required=True, help="Output directory for the ModelOpt FP8 checkpoint.")
-    p.add_argument("--dtype", choices=("bfloat16", "float16"), default="bfloat16")
-    p.add_argument("--height", type=int, default=704, help="Calibration video height (Wan2.2 TI2V-5B native: 704).")
-    p.add_argument("--width", type=int, default=1280, help="Calibration video width (Wan2.2 TI2V-5B native: 1280).")
-    p.add_argument(
-        "--num-frames",
-        type=int,
-        default=49,
-        help="Frames per calibration sample. 49 matches the typical short benchmark; "
-        "use 17 to reduce memory pressure during calibration.",
-    )
-    p.add_argument("--guidance-scale", type=float, default=5.0)
-    p.add_argument(
-        "--calib-steps",
-        type=int,
-        default=10,
-        help="Denoising steps per calibration prompt (10 is enough for amax statistics).",
-    )
-    p.add_argument("--calib-size", type=int, default=8, help="How many prompts to use for calibration.")
-    p.add_argument("--seed", type=int, default=42)
-    p.add_argument(
-        "--prompt",
-        action="append",
-        default=[],
-        help="Custom calibration prompt. Repeat to provide multiple.",
-    )
-    p.add_argument(
-        "--quantize-mha",
-        action="store_true",
-        help="Enable FP8 attention K/V/softmax quantizers. Off by default — Wan2.2's long attention "
-        "sequences amplified FP8 drift in the online ablation (see #2920).",
-    )
-    p.add_argument(
-        "--weight-block-size",
-        type=str,
-        default=None,
-        help="Per-block weight quantization as 'M,N' (e.g. '128,128'). Default per-tensor. "
-        "Note: vllm-omni's ModelOpt adapter may not yet dispatch block-wise scales — check #2924 "
-        "for the HV-1.5 investigation status before relying on this.",
-    )
-    p.add_argument("--overwrite", action="store_true", help="Replace an existing output directory.")
-    return p
-
-
-def _parse_block_size(spec: str | None) -> list[int] | None:
-    if spec is None:
-        return None
-    parts = [int(x) for x in spec.split(",") if x.strip()]
-    if len(parts) != 2:
-        raise SystemExit(f"--weight-block-size must be 'M,N' (2 ints), got {spec!r}")
-    return parts
-
-
-def _require_modelopt() -> Any:
-    try:
-        import modelopt.torch.quantization as mtq
-    except ModuleNotFoundError as exc:
-        raise SystemExit(
-            "NVIDIA ModelOpt is not installed. Install with:\n"
-            "  pip install 'nvidia-modelopt[all]'\n"
-            f"Original error: {exc}"
-        ) from exc
-    return mtq
-
-
-def _ensure_paths(args: argparse.Namespace) -> tuple[str, Path]:
-    model_path = args.model
-    output_dir = Path(args.output).expanduser().resolve()
-    if output_dir.exists():
-        if not args.overwrite:
-            raise SystemExit(f"Output directory already exists: {output_dir}\nPass --overwrite to replace it.")
-        shutil.rmtree(output_dir)
-    return model_path, output_dir
-
-
-def _select_dtype(name: str) -> torch.dtype:
-    return {"bfloat16": torch.bfloat16, "float16": torch.float16}[name]
-
-
-def _build_prompts(args: argparse.Namespace) -> list[str]:
-    prompts = args.prompt or DEFAULT_PROMPTS
-    if args.calib_size <= 0:
-        raise SystemExit("--calib-size must be positive.")
-    if len(prompts) < args.calib_size:
-        repeats = (args.calib_size + len(prompts) - 1) // len(prompts)
-        prompts = (prompts * repeats)[: args.calib_size]
-    return prompts[: args.calib_size]
-
-
-# Layers to KEEP at full precision. Wan2.2's module naming:
-# - condition_embedder: time_embedder, time_proj, text_embedder, image_embedder (I2V)
-# - patch_embedding: Conv3dLayer (already not Linear, belt-and-suspenders skip)
-# - scale_shift_table: nn.Parameter modulation (not Linear, but pattern guard)
-# - norm_out: AdaLayerNorm final
-# - proj_out: final nn.Linear
-# - timestep_proj_prepare / output_scale_shift_prepare: SP helpers
-def _filter_func_wan22(name: str) -> bool:
-    pattern = re.compile(
-        r"(proj_out.*|"
-        r".*(condition_embedder|patch_embedding|"
-        r"norm_out|scale_shift_table|"
-        r"timestep_proj_prepare|output_scale_shift_prepare).*)"
-    )
-    return pattern.match(name) is not None
-
-
-def _mha_filter_func(name: str) -> bool:
-    pattern = re.compile(
-        r".*(q_bmm_quantizer|k_bmm_quantizer|v_bmm_quantizer|softmax_quantizer|bmm2_output_quantizer).*"
-    )
-    return pattern.match(name) is not None
-
-
-def _disable_known_problematic_quantizers(mtq: Any, backbone: torch.nn.Module, *, quantize_mha: bool) -> None:
-    if not hasattr(mtq, "disable_quantizer"):
-        return
-    mtq.disable_quantizer(backbone, _filter_func_wan22)
-    if not quantize_mha:
-        mtq.disable_quantizer(backbone, _mha_filter_func)
-
-
-def _load_pipeline(model_path: str, dtype: torch.dtype) -> DiffusionPipeline:
-    pipe = DiffusionPipeline.from_pretrained(model_path, torch_dtype=dtype)
-    if hasattr(pipe, "set_progress_bar_config"):
-        pipe.set_progress_bar_config(disable=True)
-    pipe.to("cuda")
-    return pipe
-
-
-def _build_forward_loop(pipe: DiffusionPipeline, args: argparse.Namespace, prompts: list[str]):
-    generator = torch.Generator(device="cuda")
-
-    # Try setting guidance on the pipeline's guider if present (newer diffusers APIs).
-    guider = getattr(pipe, "guider", None)
-    if guider is not None and hasattr(guider, "guidance_scale"):
-        try:
-            guider.guidance_scale = args.guidance_scale
-        except Exception:
-            pass
-
-    base_kwargs = dict(
-        height=args.height,
-        width=args.width,
-        num_frames=args.num_frames,
-        num_inference_steps=args.calib_steps,
-        output_type="latent",
-    )
-
-    def forward_loop(*_unused_args, **_unused_kwargs) -> None:
-        with torch.inference_mode():
-            for idx, prompt in enumerate(prompts):
-                generator.manual_seed(args.seed + idx)
-                # Try with guidance_scale first; fall back without on TypeError
-                # for pipelines that take CFG via guider config only.
-                try:
-                    pipe(prompt=prompt, generator=generator, guidance_scale=args.guidance_scale, **base_kwargs)
-                except TypeError as exc:
-                    if "guidance_scale" not in str(exc):
-                        raise
-                    pipe(prompt=prompt, generator=generator, **base_kwargs)
-
-    return forward_loop
-
-
-def _summarize_export(output_dir: Path) -> None:
-    cfg_path = output_dir / "transformer" / "config.json"
-    if not cfg_path.exists():
-        print(f"[warn] {cfg_path} missing.", file=sys.stderr)
-        return
-    with cfg_path.open(encoding="utf-8") as f:
-        cfg = json.load(f)
-    qc = cfg.get("quantization_config")
-    if not isinstance(qc, dict):
-        print("[warn] No quantization_config in transformer/config.json.", file=sys.stderr)
-        return
-    print("Export summary:")
-    print(f"  quant_method: {qc.get('quant_method')}")
-    print(f"  quant_algo:   {qc.get('quant_algo')}")
-    producer = qc.get("producer")
-    if isinstance(producer, dict):
-        print(f"  producer:     {producer.get('name')} {producer.get('version')}")
-    print(f"  config path:  {cfg_path}")
-
-
-def _force_export_quantized_weights(backbone: torch.nn.Module, dtype: torch.dtype) -> int:
-    """Convert in-memory weights of quantized modules to actual FP8 storage.
-
-    `export_hf_checkpoint` skips this step for unknown model types (Wan2.2 isn't
-    in ModelOpt's recognized-model registry), so we must call the per-weight
-    export helper ourselves. Same workaround as the HunyuanVideo-1.5 / HunyuanImage-3
-    calibration helpers.
-    """
-    from modelopt.torch.export.quant_utils import (
-        QUANTIZATION_NONE,
-        get_quantization_format,
-        quantizer_attr_names,
-        weight_attr_names,
-    )
-    from modelopt.torch.export.unified_export_hf import _export_quantized_weight
-
-    exported = 0
-    for name, module in backbone.named_modules():
-        try:
-            quantization_format = get_quantization_format(module)
-        except Exception as exc:
-            print(f"[warn] Could not inspect quantization format for {name}: {exc}", file=sys.stderr)
-            continue
-        if quantization_format == QUANTIZATION_NONE:
-            continue
-        for weight_name in weight_attr_names(module):
-            quantizer_attrs = quantizer_attr_names(weight_name)
-            weight_quantizer = getattr(module, quantizer_attrs.weight_quantizer, None)
-            if weight_quantizer is None or not getattr(weight_quantizer, "is_enabled", False):
-                continue
-            _export_quantized_weight(module, dtype, weight_name)
-            exported += 1
-    return exported
-
-
-def _wan22_quant_config_block(weight_block_size: list[int] | None = None) -> dict:
-    """Mirror ModelOpt FP8 metadata expected by vllm-omni's adapter (#2913)."""
-    weights_cfg: dict = {"dynamic": False, "num_bits": 8, "type": "float"}
-    if weight_block_size is not None:
-        weights_cfg["strategy"] = "block"
-        weights_cfg["block_structure"] = f"{weight_block_size[0]}x{weight_block_size[1]}"
-    return {
-        "config_groups": {
-            "group_0": {
-                "input_activations": {"dynamic": False, "num_bits": 8, "type": "float"},
-                "weights": weights_cfg,
-                "targets": ["Linear"],
-            }
-        },
-        "ignore": [
-            "condition_embedder*",
-            "norm_out*",
-            "output_scale_shift_prepare*",
-            "patch_embedding*",
-            "proj_out*",
-            "scale_shift_table*",
-            "timestep_proj_prepare*",
-        ],
-        "producer": {"name": "modelopt"},
-        "quant_algo": "FP8",
-        "quant_method": "modelopt",
-    }
-
-
-def _patch_quant_config(output_dir: Path, weight_block_size: list[int] | None = None) -> None:
-    """Inject quant_algo: FP8 + config_groups into each transformer's config.json
-    so vllm-omni's adapter (#2913) recognises the checkpoint as ModelOpt FP8.
-
-    Patches both ``transformer`` and ``transformer_2`` (A14B) when present."""
-    for sub in ("transformer", "transformer_2"):
-        cfg_path = output_dir / sub / "config.json"
-        if not cfg_path.exists():
-            continue
-        with cfg_path.open(encoding="utf-8") as f:
-            cfg = json.load(f)
-
-        new_qc = _wan22_quant_config_block(weight_block_size=weight_block_size)
-        existing = cfg.get("quantization_config")
-        if isinstance(existing, dict):
-            producer = existing.get("producer")
-            if isinstance(producer, dict):
-                new_qc["producer"] = producer
-
-        cfg["quantization_config"] = new_qc
-        with cfg_path.open("w", encoding="utf-8") as f:
-            json.dump(cfg, f, indent=2)
-
-
-def _list_transformers(pipe: DiffusionPipeline) -> list[tuple[str, torch.nn.Module]]:
-    """Return [(attr_name, module)] for every DiT on the pipeline.
-
-    Wan2.2 A14B has both ``transformer`` (low-noise) and ``transformer_2``
-    (high-noise). TI2V-5B has only ``transformer``.
-    """
-    out = []
-    for attr in ("transformer", "transformer_2"):
-        mod = getattr(pipe, attr, None)
-        if mod is not None:
-            out.append((attr, mod))
-    return out
-
-
-def _save_pipeline_with_fp8_transformer(
-    pipe: DiffusionPipeline,
-    model_path: str,
-    output_dir: Path,
-    max_shard_size: str = "5GB",
-) -> None:
-    """Copy source dir verbatim minus transformer dirs, then save each quantized DiT.
-
-    Handles A14B's dual transformer (``transformer`` + ``transformer_2``) as well
-    as the single-DiT TI2V-5B.
-    """
-    from modelopt.torch.export.diffusers_utils import hide_quantizers_from_state_dict
-
-    src = Path(model_path)
-    if not src.exists():
-        from huggingface_hub import snapshot_download
-
-        src = Path(snapshot_download(model_path))
-
-    if output_dir.exists():
-        shutil.rmtree(output_dir)
-    shutil.copytree(src, output_dir, ignore=shutil.ignore_patterns("transformer", "transformer_2"))
-
-    for attr, backbone in _list_transformers(pipe):
-        transformer_out = output_dir / attr
-        # Pass the nn.Module (transformer), not the Pipeline wrapper.
-        with hide_quantizers_from_state_dict(backbone):
-            backbone.save_pretrained(
-                str(transformer_out),
-                safe_serialization=True,
-                max_shard_size=max_shard_size,
-            )
-
-
-def main() -> None:
-    args = _build_parser().parse_args()
-    if not torch.cuda.is_available():
-        raise SystemExit("CUDA is required for ModelOpt FP8 quantization.")
-
-    mtq = _require_modelopt()
-    model_path, output_dir = _ensure_paths(args)
-    dtype = _select_dtype(args.dtype)
-    prompts = _build_prompts(args)
-    weight_block_size = _parse_block_size(args.weight_block_size)
-
-    print("Quantization plan:")
-    print(f"  input:           {args.model}")
-    print(f"  output:          {output_dir}")
-    print(f"  dtype:           {dtype}")
-    print(f"  height/width:    {args.height}x{args.width}")
-    print(f"  num_frames:      {args.num_frames}")
-    print(f"  calib_size:      {len(prompts)}")
-    print(f"  calib_steps:     {args.calib_steps}")
-    print(f"  quantize_mha:    {args.quantize_mha}")
-    print(
-        f"  weight strategy: {'block-wise ' + str(weight_block_size) if weight_block_size else 'per-tensor (default)'}"
-    )
-
-    pipe = _load_pipeline(model_path, dtype)
-    transformers = _list_transformers(pipe)
-    if not transformers:
-        raise SystemExit("Pipeline has no transformer or transformer_2 attribute.")
-    print(f"  found {len(transformers)} transformer(s): {', '.join(a for a, _ in transformers)}")
-
-    quant_config = copy.deepcopy(mtq.FP8_DEFAULT_CFG)
-    if weight_block_size is not None:
-        quant_config["quant_cfg"]["*weight_quantizer"] = {
-            "num_bits": (4, 3),
-            "block_sizes": {-1: weight_block_size[1], -2: weight_block_size[0]},
-        }
-        print(
-            f"  -> overriding weight quantizer with block_sizes={weight_block_size} "
-            f"({weight_block_size[0]}x{weight_block_size[1]} tiles)"
-        )
-
-    forward_loop = _build_forward_loop(pipe, args, prompts)
-
-    # Quantize each DiT. The forward_loop runs the full pipeline, so quantizers
-    # on every attached transformer (A14B: transformer + transformer_2) get
-    # calibrated during the same passes.
-    for attr, backbone in transformers:
-        print(f"\nQuantizing {attr}...")
-        quantized = mtq.quantize(backbone, quant_config, forward_loop)
-        if quantized is not None:
-            setattr(pipe, attr, quantized)
-        _disable_known_problematic_quantizers(mtq, getattr(pipe, attr), quantize_mha=args.quantize_mha)
-
-    # Export weights to FP8 only AFTER all transformers are calibrated. Exporting
-    # inside the loop would convert transformer's weights to real FP8, and the
-    # next transformer's forward_loop (full pipeline) would then fake-quantize an
-    # already-FP8 weight -> "fake_e4m3fy not implemented for Float8_e4m3fn".
-    print("\nForcing FP8 weight serialization (Wan2.2 isn't in ModelOpt's recognized-model registry,")
-    print("so we have to call the per-weight export helper ourselves)...")
-    total_exported = 0
-    for attr, backbone in _list_transformers(pipe):
-        exported = _force_export_quantized_weights(backbone, dtype)
-        print(f"  -> {exported} weights converted to FP8 in {attr}")
-        total_exported += exported
-
-    if total_exported == 0:
-        raise SystemExit(
-            "No quantized weights were exported. Calibration may have skipped every layer "
-            "(check the disable_quantizer regex) or `mtq.quantize` did not actually wrap any "
-            "weight quantizers."
-        )
-
-    print("\nSaving pipeline with FP8 transformer(s)...")
-    _save_pipeline_with_fp8_transformer(pipe, model_path, output_dir)
-    _patch_quant_config(output_dir, weight_block_size=weight_block_size)
-    print(f"Saved to: {output_dir}")
-    _summarize_export(output_dir)
-
-    print("\nNext: validate the checkpoint with vllm-omni:")
-    print(
-        "  python examples/offline_inference/text_to_video/text_to_video.py \\\n"
-        f"    --model {output_dir} \\\n"
-        "    --quantization fp8 \\\n"
-        "    --prompt 'A dog running across a field of golden wheat.' \\\n"
-        f"    --height {args.height} --width {args.width} --num-frames {args.num_frames} \\\n"
-        "    --num-inference-steps 30 --guidance-scale 5.0 --seed 42 \\\n"
-        "    --output outputs/wan22_modelopt_fp8.mp4"
-    )
-    print(
-        "\n  (--quantization fp8 is auto-upgraded to ModelOpt FP8 at runtime because the "
-        "checkpoint's config.json has modelopt metadata.)"
-    )
-
-
-if __name__ == "__main__":
-    main()

recipes/MiniMaxAI/MiniMax-H3-NPU.md

@@ -79,7 +79,8 @@ sharing the tokenizer, processor, text encoder, and VAEs from `FL2VA`.
 ### Multi-NPU: 768P combined-service configuration
 
 Use Ulysses sequence parallelism degree 8, text-encoder tensor parallelism
-degree 8, native tiled VAE patch parallelism degree 8, and layerwise offload:
+degree 8, native tiled VAE patch parallelism degree 8, and distributed
+layerwise offload:
 
 ```bash
 export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
@@ -98,7 +99,7 @@ vllm serve "${MODEL}" \
   --usp 8 \
   --ring 1 \
   --text-encoder-tp-size 8 \
-  --enable-layerwise-offload \
+  --enable-distributed-layerwise-offload \
   --vae-parallel-mode tile \
   --vae-use-tiling \
   --vae-patch-parallel-size 8 \
@@ -112,6 +113,11 @@ H3 is CFG-distilled, so `--cfg-parallel-size` must remain 1.
 The same endpoint accepts `task=t2va`, `task=fl2va`, and `task=ref2va`; no
 partition restart is required. Layerwise offload applies to both DiTs.
 
+On Atlas 800I A3 (64 GB HBM per device) the combined service does not fit at
+768P without offloading or sharding: use distributed layerwise offload (as
+above) or HSDP — see
+[§ Memory and attention optimizations](#memory-and-attention-optimizations-a3).
+
 ### Optional optimizations
 
 Two independent optimizations may be enabled on top of the configuration
@@ -134,6 +140,63 @@ Keep `--ring 1` when using RainFusion: the `rf_v2` kernel ranks key blocks
 over the whole sequence, so ring parallelism would split away the keys it
 needs. Scale with `--usp` instead.
 
+## Memory and attention optimizations (A3)
+
+### Fitting 768P into 64 GB HBM: distributed layerwise offload or HSDP
+
+Each Atlas 800I A3 NPU has 64 GB of HBM, which is not enough for the
+combined MiniMax-H3 service at 768P. Enable **one** of the following at
+server startup:
+
+**Distributed layerwise offload** — DiT layers are offloaded with parameters
+gathered across the parallel group instead of replicated per rank:
+
+```bash
+  --enable-distributed-layerwise-offload
+```
+
+Measured peak NPU memory is about 45 GB per device for Ref2VA with a 13.88 s
+input video generating a 15 s 768P (1344x768) output video. Host (CPU) memory
+usage is high with this option.
+
+**HSDP** — hybrid sharded data parallelism for the DiT parameters. The
+multi-stream memory-reuse knob is mandatory with this flag:
+
+```bash
+export MULTI_STREAM_MEMORY_REUSE=2
+```
+
+```bash
+  --use-hsdp
+```
+
+Host memory usage is small, but large shapes may still OOM; HBM usage
+optimizations for this path are ongoing.
+
+### FLASH_ATTN backend with MindIE-SD
+
+Keep `--diffusion-attention-backend FLASH_ATTN` and install MindIE-SD (see
+[§ Environment](#environment)). On NPU this backend carries most of the
+memory-reduction and performance work: a mask-free packed varlen path that
+never materializes the quadratic `full_qk` padding mask, and K/V prefix
+slicing, both driven by the packed `cu_seqlens` metadata emitted by the H3
+transformer.
+
+### Optional: LaserAttention fused kernel
+
+For an additional attention speedup, select the Ascend LaserAttention fused
+kernel before starting the server:
+
+```bash
+export MINDIE_SD_FA_TYPE="ascend_laser_attention"
+```
+
+This requires the FLASH_ATTN backend and MindIE-SD. H3 automatically applies
+exact power-of-two input pre-scaling (`laser_input_scale=256`) so the
+kernel's fp16 workspace cannot overflow on outlier activations. Measured
+speedup numbers will be added here.
+
+
 ## HTTP API examples
 
 The request format is identical to the GPU recipe; see
@@ -154,8 +217,8 @@ configuration above:
 
 | Workload | Configuration |
 |----------|---------------|
-| T2VA, 209 frames, 1344x768 | TE TP8, layerwise offload, Ulysses 8, VPP8 tile, regional compile |
+| T2VA, 209 frames, 1344x768 | TE TP8, distributed layerwise offload, Ulysses 8, VPP8 tile, regional compile |
-| Ref2VA (prompt + video), 124 frames, 1344x768 | TE TP8, layerwise offload, Ulysses 8, VPP8 tile, regional compile |
+| Ref2VA (prompt + video), 124 frames, 1344x768 | TE TP8, distributed layerwise offload, Ulysses 8, VPP8 tile, regional compile |
 
 These measurements describe the validated shapes rather than a general
 throughput guarantee.

recipes/MiniMaxAI/MiniMax-H3-Spark-GB10.md

@@ -4,6 +4,17 @@ This recipe uses online FP8 weight quantization, tiled VAE decode, and a single
 resident partition. GB10 is a unified-memory platform, so unlike the discrete-GPU
 recipes it uses **no offload of any kind** — see the capacity note below.
 
+Validated on:
+
+- Host: DGX Spark (GB10), aarch64
+- GPUs: 1 (unified memory)
+- Driver: <FILL_DRIVER_VERSION>
+- vLLM: 0.26.0
+- vLLM-Omni: `main` at `e1aa6eae75c460cd1893bc320546e81e66973831`
+- Workloads: T2VA and Ref2VA, 960x576, `duration=8.0`, 50 steps, `flow_shift=12`,
+  `seed=1101`
+
+
 ## Capacity requirements
 
 | Resource | DGX Spark (GB10) |
@@ -11,7 +22,8 @@ recipes it uses **no offload of any kind** — see the capacity note below.
 | Unified memory | 128 GB LPDDR5X (~121 GiB usable) |
 | GPUs | 1 |
 | Checkpoint storage | 135 GiB per partition |
-| Measured peak allocator high-water (FP8) | 97.7 GiB |
+| Measured peak allocator high-water, T2VA (FP8) | 97.7 GiB |
+| Measured peak allocator high-water, Ref2VA (FP8) | 102.8 GiB |
 
 `FL2VA` and `Ref2VA` are separate 135 GiB checkpoint partitions. Start one server
 at a time.
@@ -29,9 +41,21 @@ math relative to the RTX and datacenter recipes:
   fit in 121 GiB. Online FP8 quantizes the DiT only (62 GiB to ~31 GiB); the
   Qwen3-VL text encoder and both VAEs stay BF16.
 
-With ~97.7 GiB of the pool held by the allocator at peak, there is roughly 23 GiB
+With ~97.7 GiB of the pool held by the allocator at peak, T2VA leaves roughly
-of headroom for the OS, page cache, and any other process on the box. Treat this
+23 GiB of headroom for the OS, page cache, and any other process on the box.
-platform as single-tenant while a request is in flight.
+Ref2VA is tighter on both counts. The allocator high-water rises to 102.8 GiB,
+and the allocator figure understates true pool usage.
+
+Sampling `/proc/meminfo` at 1 Hz across a 50-step Ref2VA request on a host with
+`MemTotal: 127600524 kB` (121.7 GiB), `MemAvailable` started at 8.1 GiB, fell to
+a trough of **7.4 GiB**, and recovered to 8.9 GiB. At the trough the pool held
+roughly **114.3 GiB** — 11.4 GiB more than the 102.8 GiB the allocator reports,
+which is the CUDA context, non-PyTorch allocations, and page cache the header
+does not count.
+
+Treat this platform as strictly single-tenant for Ref2VA. There is no room for a
+second process, and adding reference images, reference videos, or a larger output
+shape will run into the OOM killer.
 
 ## One GB10: 960x576, 8 seconds
 
@@ -94,6 +118,52 @@ ffprobe -v error -show_entries \
 Both requests return `200 OK` with an MP4 body: H.264 video at the requested
 geometry plus a 32 kHz stereo AAC track.
 
+## One GB10: Ref2VA, 960x576, 8 seconds
+
+`FL2VA` and `Ref2VA` are separate 135 GiB partitions and only one fits at a time.
+Stop the FL2VA server before starting this one.
+
+```bash
+CUDA_VISIBLE_DEVICES=0 \
+FLASHINFER_DISABLE_VERSION_CHECK=1 \
+VLLM_WORKER_MULTIPROC_METHOD=spawn \
+VLLM_OMNI_VIDEO_SYNC_TIMEOUT=14400 \
+vllm serve /path/to/MiniMax-H3/Ref2VA \
+  --omni --trust-remote-code --host 0.0.0.0 --port 8000 \
+  --init-timeout 3600 \
+  --num-gpus 1 --tensor-parallel-size 1 --text-encoder-tp-size 1 \
+  --usp 1 --ring 1 --vae-patch-parallel-size 1 \
+  --vae-parallel-mode tile --vae-use-tiling \
+  --quantization fp8 --enforce-eager \
+  --diffusion-attention-backend CUDNN_ATTN
+```
+
+The 7200 s timeout used for T2VA is too short here: a 50-step Ref2VA request
+takes over an hour on this platform. Use 14400 s.
+
+Unlike `t2va`, `ref2va` defaults to a 16:9 output ratio, so `aspect_ratio` can be
+omitted when `width` and `height` are supplied.
+
+```bash
+curl --fail-with-body -sS -X POST http://127.0.0.1:8000/v1/videos/sync \
+  -D ref2va-headers.txt \
+  -w 'client_e2e_s=%{time_total}\n' \
+  --max-time 14400 \
+  -F 'input_reference=@/path/to/reference.jpg;type=image/jpeg' \
+  -F 'prompt=A hand rests on a wooden table in warm evening light, then slowly opens and turns toward the camera, with quiet room ambience.' \
+  -F 'width=960' \
+  -F 'height=576' \
+  -F 'fps=24' \
+  -F 'num_inference_steps=50' \
+  -F 'flow_shift=12' \
+  -F 'seed=1101' \
+  -F 'extra_params={"task":"ref2va","duration":8.0,"audio_flow_shift":3.0}' \
+  -o h3-gb10-ref2va.mp4
+```
+
+The response is `200 OK` with an MP4 body: H.264 at the requested geometry plus a
+32 kHz stereo AAC track. `ffprobe` reports 8.032 s for `duration=8.0`.
+
 ## Measured latency
 
 Single GB10, FP8, eager, cuDNN attention, tiled VAE, one request at a time:
@@ -102,32 +172,69 @@ Single GB10, FP8, eager, cuDNN attention, tiled VAE, one request at a time:
 | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
 | T2VA, 4 s, smoke shape | 10 | — | — | 8.68 s | — | 0.49 s | 95.9 s | — |
 | T2VA, 8 s, 960x576 | 50 | 0.25 s | 2088 s | 42.61 s | 70 s | 4.84 s | 2169.4 s (36 min 9 s) | 97.7 GiB |
+| Ref2VA, 8 s, 960x576, one image (3 runs) | 10 | 8.43-10.94 s | 665.5-748.8 s | 66.55-74.88 s | 67.9-69.8 s | 3.63 s | 770.3-861.1 s | 102.8 GiB |
+| Ref2VA, 8 s, 960x576, one image | 50 | 9.66 s | 4039.6 s | 80.79 s | 69.4 s | 3.63 s | 4157.0 s (69 min 17 s) | 102.8 GiB |
 
 How these were measured:
 
 - Stage times come from `--enable-diffusion-pipeline-profiler`, read from the
-  `X-Stage-Durations` response header of `/v1/videos/sync`.
+  `X-Stage-Durations` response header of `/v1/videos/sync`. The keys are
+  `MiniMaxH3Pipeline.encode_prompt` (text encode),
+  `MiniMaxH3Pipeline.diffuse` (denoise), and `MiniMaxH3Pipeline.decode`
+  (VAE decode).
+- MP4 mux is not a header field. It is the
+  `Video response encoding (MP4 bytes)` line in the server log.
 - Peak memory is the `X-Peak-Memory-MB` header, which reports the CUDA allocator
   high-water mark (`torch.cuda.max_memory_reserved`) for the request. It excludes
   the CUDA context and non-PyTorch allocations, so true pool usage is somewhat
   higher. `nvidia-smi --query-gpu=memory.used` is not usable on GB10 — unified
-  memory has no discrete VRAM to report and the field returns `[N/A]`.
+  memory has no discrete VRAM to report and the field returns `[N/A]`. See the
-- Text encode and VAE decode were measured on a separate 10-step run at the same
+  capacity section for a `/proc/meminfo` cross-check.
-  960x576 / 8 s geometry. Both are independent of step count, so they transfer to
+- For T2VA, text encode and VAE decode were measured on a separate 10-step run at
-  the 50-step row unchanged.
+  the same 960x576 / 8 s geometry. Both are independent of step count, so they
+  transfer to the 50-step row unchanged. The Ref2VA MP4 mux figure transfers the
+  same way, from the 10-step run at identical output geometry and duration.
+- Ref2VA peak memory is byte-identical between the 10-step and 50-step runs
+  (`X-Peak-Memory-MB: 105318.000` in both), confirming that peak is set by output
+  geometry and reference input rather than step count.
 - Stage times do not sum exactly to end-to-end. Queueing, result transfer, and
   engine bookkeeping sit outside the profiled stages.
 
 Denoise dominates at 96% of end-to-end, so step count and geometry are the only
 knobs that materially change the wall clock on this platform.
 
-Repeated identical 10-step requests varied by up to 23% in denoise time
+Ref2VA costs 1.92x the wall clock of T2VA at the same geometry and step count:
+4157.0 s versus 2169.4 s. Text encoding shows the most dramatic ratio — 9.66 s
+versus 0.25 s, 39x — but at 0.2% of end-to-end it is not what makes Ref2VA slow.
+The cost is in denoise. A single reference image expands the Qwen3-VL
+presentation to 6883 tokens (logged as `MiniMax H3 ref2va Qwen presentation:
+6883 tokens, 1 reference images`), and those tokens sit in the attention context
+of every denoise step. Per-step time rises from 42.61 s to 80.79 s, and that
+1.90x multiplies across all 50 steps. VAE decode is unchanged at ~69 s, as
+expected for an identical output shape.
+
+Repeated identical 10-step T2VA requests varied by up to 23% in denoise time
 (397 s to 490 s) on a machine that had already been under sustained load. Treat
 these as single-run measurements on one machine, not a throughput guarantee, and
 expect the slower end of that range for back-to-back jobs.
 
+Ref2VA per-step time is load-dependent in the same way. On an idle machine the
+first 10-step request ran at 66.55 s per step. The 50-step request that followed
+occupied the box for 69 consecutive minutes and averaged 80.79 s per step. Two
+further 10-step requests taken immediately afterwards settled at 74.88 s and
+74.31 s — 12.5% slower than the idle run, and within 0.8% of each other, so this
+is a stable thermal state rather than measurement noise.
+
+Plan for 81 s per step when sizing a full 50-step Ref2VA job; 66 s per step is
+only reachable on a cold machine and does not hold for the length of one request.
+
+Ref2VA text encode converged downward across the four runs (10.94 s, 9.66 s,
+8.52 s, 8.43 s) as first-touch costs fell away; treat ~8.5 s as steady state.
+VAE decode was stable at 67.9-69.8 s throughout.
+
 Set `VLLM_OMNI_VIDEO_SYNC_TIMEOUT` well above the expected request time — the
-default 1800 s is shorter than a 50-step run on this platform.
+default 1800 s is shorter than a 50-step run on this platform, and 7200 s is
+shorter than a 50-step Ref2VA run.
 
 ## Known limitations
 
@@ -139,11 +246,17 @@ default 1800 s is shorter than a 50-step run on this platform.
 - `t2va` rejects requests without an explicit `aspect_ratio`. When `width` and
   `height` are both supplied they take precedence and `aspect_ratio` only has to
   name one of the supported ratios.
-- Sustained load degrades throughput. See the variance note above.
+- Sustained load degrades throughput. See the variance notes above.
 - Only one partition is resident. For Ref2VA, stop the FL2VA server and restart
-  the same command with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA reference video
+  with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA with one reference image is measured
-  count and prompt length increase activation memory; begin with one request at
+  above; reference videos and additional images push the token count higher and
-  a time and keep the short edge at 576.
+  were not measured. With `MemAvailable` bottoming out at 7.4 GiB during a
+  single-image request, there is very little room to grow — re-measure before
+  adding references or raising the output shape.
+- Ref2VA requires a vLLM-Omni build newer than `v0.26.0`. See the version note
+  under **Validated on**: FP8 weight loading and image-only Ref2VA are both
+  broken on `release/v0.26.0`.suggestion is  `v0.26.1`.
 - Online FP8 is incompatible with layerwise offload — the offload path produces a
   weight stride the Cutlass FP8 kernel rejects. This is not a practical
   restriction here since offload is unusable on GB10 anyway.
+```

recipes/README.md

@@ -19,6 +19,11 @@ add files for this repo. Use one Markdown file per model family by default.
 > Individual pages resolve at `https://recipes.vllm.ai/<provider>/<model-id>`,
 > e.g. [`bosonai/higgs-audio-v3-tts-4b`](https://recipes.vllm.ai/bosonai/higgs-audio-v3-tts-4b).
 
+The `Recipe` column in the Supported Models documentation links to the
+published recipe when available and otherwise to the corresponding recipe in
+this directory. The recipe files remain the source of truth for commands and
+validation details.
+
 Example layout:
 
 ```text

tests/config/test_omni_config.py

@@ -579,6 +579,7 @@ def test_diffusion_parallel_config_keeps_current_diffusion_parallel_surface():
     assert cfg.data_parallel_size == 3
     assert cfg.cfg_parallel_size == 3
     assert cfg.mask_sp_padding is True
+    assert cfg.vae_parallel_mode == "auto"
     assert cfg.world_size == 72
 
 

tests/diffusion/attention/test_flash_attn.py

@@ -9,6 +9,10 @@ This script tests two main scenarios:
 2. Case 2: Comparing FlashAttention and SDPA backends for batch_size=2 with padding
 """
 
+import sys
+from types import SimpleNamespace
+from unittest.mock import Mock
+
 import pytest
 import torch
 
@@ -371,6 +375,264 @@ def test_packed_varlen_metadata_must_be_complete(monkeypatch):
         impl.forward_cuda(query, query, query, metadata)
 
 
+# ---------------------------------------------------------------------------
+# NPU mask-free packed attention (PR #5891).
+#
+# These tests cover the backend-side NPU branches that ``forward_fa_npu`` adds:
+#   - boundary resolution in ``_resolve_packed_seq_npu`` (pure Python, no device
+#     sync, no MindIE-SD import);
+#   - env dispatch in ``forward_fa_npu`` (which op a packed forward takes);
+#   - the laser input pre-scaling math in ``_forward_prefix_kv_slice_npu``.
+#
+# They run on CPU without a real NPU by injecting a fake ``mindiesd`` module
+# into ``sys.modules`` (same pattern as ``test_paged_attention`` /
+# ``benchmarks/conftest``). No production code is exercised for real kernels.
+
+
+def _npu_impl(causal: bool = False) -> FlashAttentionImpl:
+    return FlashAttentionImpl(num_heads=2, head_size=4, softmax_scale=0.5, causal=causal)
+
+
+def _fake_mindiesd(monkeypatch, *, attention_forward=None, attention_forward_varlen=None):
+    """Install a stub ``mindiesd`` so local ``from mindiesd import ...`` works.
+
+    Restored automatically by monkeypatch. Defaults are no-op callables so the
+    top-level import in ``forward_fa_npu`` succeeds even when the test mocks the
+    instance methods that would otherwise call them.
+    """
+    fake = SimpleNamespace(
+        attention_forward=attention_forward or Mock(return_value=torch.zeros(1)),
+        attention_forward_varlen=attention_forward_varlen or Mock(return_value=torch.zeros(1)),
+    )
+    monkeypatch.setitem(sys.modules, "mindiesd", fake)
+    return fake
+
+
+# --- Test group A: boundary resolution (_resolve_packed_seq_npu) -------------
+
+
+def test_resolve_packed_seq_accepts_real_plus_pad_contract():
+    impl = _npu_impl()
+    q = torch.randn(1, 8, 2, 4)
+    cu = torch.tensor([0, 5, 8], dtype=torch.int32)
+    extra = {"cu_seqlens_q": cu, "cu_seqlens_k": cu, "max_seqlen_q": 5, "max_seqlen_k": 5}
+
+    assert impl._resolve_packed_seq_npu(q, q, extra) == ([5, 8], [5, 8])
+
+
+def test_resolve_packed_seq_single_document_no_padding():
+    impl = _npu_impl()
+    q = torch.randn(1, 8, 2, 4)
+    cu = torch.tensor([0, 8], dtype=torch.int32)
+    extra = {"cu_seqlens_q": cu, "cu_seqlens_k": cu, "max_seqlen_q": 8, "max_seqlen_k": 8}
+
+    assert impl._resolve_packed_seq_npu(q, q, extra) == ([8], [8])
+
+
+@pytest.mark.parametrize(
+    "case",
+    [
+        "causal",
+        "missing_key",
+        "batch_ne_1",
+        "cu_too_long",
+        "cu_qk_mismatch",
+        "max_seqlen_not_int",
+        "used_gt_total",
+        "used_zero",
+        "pad_longer_than_real",
+    ],
+)
+def test_resolve_packed_seq_rejects_malformed_metadata(case):
+    """Any metadata outside the exact [real, pad] contract returns None so the
+    caller falls back to the masked path."""
+    cu3 = torch.tensor([0, 5, 8], dtype=torch.int32)
+    cu2 = torch.tensor([0, 8], dtype=torch.int32)
+    cu4 = torch.tensor([0, 3, 5, 8], dtype=torch.int32)
+    cu_short = torch.tensor([0, 3, 8], dtype=torch.int32)
+    base = {"cu_seqlens_q": cu3, "cu_seqlens_k": cu3, "max_seqlen_q": 5, "max_seqlen_k": 5}
+    q = torch.randn(1, 8, 2, 4)
+
+    impl = _npu_impl(causal=(case == "causal"))
+    if case == "missing_key":
+        extra = {"cu_seqlens_q": cu3, "max_seqlen_q": 5}  # 3 of 4 keys absent
+    elif case == "batch_ne_1":
+        q = torch.randn(2, 8, 2, 4)
+        extra = base
+    elif case == "cu_too_long":
+        extra = {**base, "cu_seqlens_q": cu4, "cu_seqlens_k": cu4}
+    elif case == "cu_qk_mismatch":
+        extra = {**base, "cu_seqlens_q": cu3, "cu_seqlens_k": cu2}
+    elif case == "max_seqlen_not_int":
+        extra = {**base, "max_seqlen_q": 5.0}
+    elif case == "used_gt_total":
+        extra = {**base, "max_seqlen_q": 9}  # 9 > total length 8
+    elif case == "used_zero":
+        extra = {**base, "max_seqlen_q": 0, "max_seqlen_k": 0}
+    elif case == "pad_longer_than_real":
+        # real=3, pad=5: the real document must be the longer one.
+        extra = {
+            "cu_seqlens_q": cu_short,
+            "cu_seqlens_k": cu_short,
+            "max_seqlen_q": 3,
+            "max_seqlen_k": 3,
+        }
+    else:
+        extra = base
+
+    assert impl._resolve_packed_seq_npu(q, q, extra) is None
+
+
+# --- Test group B: env dispatch in forward_fa_npu (current behavior) --------
+
+
+def _npu_impl_with_mocked_paths() -> tuple[FlashAttentionImpl, torch.Tensor]:
+    """FlashAttentionImpl whose two packed paths are Mocks returning a sentinel.
+
+    Lets a test assert which branch ``forward_fa_npu`` dispatched to without
+    running any real kernel.
+    """
+    impl = _npu_impl()
+    sentinel = torch.tensor([1.0])
+    impl._forward_varlen_packed_npu = Mock(return_value=sentinel)
+    impl._forward_prefix_kv_slice_npu = Mock(return_value=sentinel)
+    return impl, sentinel
+
+
+def test_npu_env_unset_uses_varlen(monkeypatch):
+    monkeypatch.delenv("MINDIE_SD_FA_TYPE", raising=False)
+    _fake_mindiesd(monkeypatch)
+    impl, _ = _npu_impl_with_mocked_paths()
+    metadata = AttentionMetadata(extra={"npu_attn_varlen": True})
+
+    impl.forward_fa_npu(torch.randn(1, 8, 2, 4), *[torch.randn(1, 8, 2, 4)] * 2, metadata)
+
+    impl._forward_varlen_packed_npu.assert_called_once()
+    impl._forward_prefix_kv_slice_npu.assert_not_called()
+
+
+def test_npu_env_laser_uses_slice(monkeypatch):
+    monkeypatch.setenv("MINDIE_SD_FA_TYPE", "ascend_laser_attention")
+    _fake_mindiesd(monkeypatch)
+    impl, _ = _npu_impl_with_mocked_paths()
+    metadata = AttentionMetadata(extra={"npu_attn_varlen": True})
+
+    impl.forward_fa_npu(torch.randn(1, 8, 2, 4), *[torch.randn(1, 8, 2, 4)] * 2, metadata)
+
+    impl._forward_prefix_kv_slice_npu.assert_called_once()
+    impl._forward_varlen_packed_npu.assert_not_called()
+
+
+@pytest.mark.parametrize("fa_type", ["prompt_flash_attn", "fused_attn_score", "ascend_laser_attenton", "garbage"])
+def test_npu_env_non_laser_value_falls_back_to_varlen(monkeypatch, fa_type):
+    """Locks in the CURRENT dispatch behavior (PR #5891).
+
+    Any value other than ``ascend_laser_attention`` — including the valid
+    ``prompt_flash_attn``/``fused_attn_score`` and typos — is silently routed to
+    the TND varlen op, which cannot honor ``MINDIE_SD_FA_TYPE``. This is review
+    comment #1 on the PR and is intentionally captured here as a regression
+    net: update this test when the dispatch starts honoring/rejecting these.
+    """
+    monkeypatch.setenv("MINDIE_SD_FA_TYPE", fa_type)
+    _fake_mindiesd(monkeypatch)
+    impl, _ = _npu_impl_with_mocked_paths()
+    metadata = AttentionMetadata(extra={"npu_attn_varlen": True})
+
+    impl.forward_fa_npu(torch.randn(1, 8, 2, 4), *[torch.randn(1, 8, 2, 4)] * 2, metadata)
+
+    impl._forward_varlen_packed_npu.assert_called_once()
+    impl._forward_prefix_kv_slice_npu.assert_not_called()
+
+
+def test_npu_varlen_opt_in_unset_takes_mask_path(monkeypatch):
+    """Models that do not set ``npu_attn_varlen`` (e.g. Wan/Cosmos) keep using
+    the existing masked attention_forward path; the new branches are skipped."""
+    fake_forward = Mock(return_value=torch.zeros(1, 8, 2, 4))
+    _fake_mindiesd(monkeypatch, attention_forward=fake_forward)
+    impl, _ = _npu_impl_with_mocked_paths()
+    metadata = AttentionMetadata(
+        attn_mask=torch.tensor([[True, True, True, True, True, False, False, False]]),
+        extra={},  # no npu_attn_varlen opt-in
+    )
+    q = torch.randn(1, 8, 2, 4)
+
+    out = impl.forward_fa_npu(q, q, q, metadata)
+
+    impl._forward_varlen_packed_npu.assert_not_called()
+    impl._forward_prefix_kv_slice_npu.assert_not_called()
+    fake_forward.assert_called_once()
+    assert out is fake_forward.return_value
+
+
+# --- Test group C: laser input pre-scaling in _forward_prefix_kv_slice_npu --
+
+
+def test_prefix_kv_slice_applies_laser_input_scaling(monkeypatch):
+    monkeypatch.setenv("MINDIE_SD_FA_TYPE", "ascend_laser_attention")
+    captured: dict = {}
+
+    def fake_attention_forward(query, key, value, **kwargs):
+        captured["query"] = query
+        captured["key"] = key
+        captured["value"] = value
+        captured.update(kwargs)
+        return torch.ones_like(query)  # deterministic stand-in kernel output
+
+    _fake_mindiesd(monkeypatch, attention_forward=fake_attention_forward)
+    impl = _npu_impl()  # softmax_scale == 0.5
+    q = torch.randn(1, 8, 2, 4)
+    cu = torch.tensor([0, 5, 8], dtype=torch.int32)
+    extra = {
+        "cu_seqlens_q": cu,
+        "cu_seqlens_k": cu,
+        "max_seqlen_q": 5,
+        "max_seqlen_k": 5,
+        "laser_input_scale": 256.0,
+    }
+
+    out = impl._forward_prefix_kv_slice_npu(q, q, q, extra)
+
+    # K/V sliced to the valid prefix (used_k == 5); q keeps full length.
+    assert captured["key"].shape == (1, 5, 2, 4)
+    assert captured["value"].shape == (1, 5, 2, 4)
+    assert captured["query"].shape == (1, 8, 2, 4)
+    assert captured["attn_mask"] is None
+    # Pre-divide q/k/v by the factor and compensate the kernel scale by its
+    # square (exact for power-of-two); output scaled back by the factor.
+    torch.testing.assert_close(captured["query"], q / 256.0)
+    torch.testing.assert_close(captured["key"], q[:, :5] / 256.0)
+    assert captured["scale"] == pytest.approx(0.5 * 256.0**2)
+    torch.testing.assert_close(out, torch.ones(1, 8, 2, 4) * 256.0)
+
+
+def test_prefix_kv_slice_no_scaling_without_factor(monkeypatch):
+    monkeypatch.setenv("MINDIE_SD_FA_TYPE", "ascend_laser_attention")
+    captured: dict = {}
+
+    def fake_attention_forward(query, key, value, **kwargs):
+        captured["query"] = query
+        captured.update(kwargs)
+        return torch.ones_like(query)
+
+    _fake_mindiesd(monkeypatch, attention_forward=fake_attention_forward)
+    impl = _npu_impl()
+    q = torch.randn(1, 8, 2, 4)
+    cu = torch.tensor([0, 5, 8], dtype=torch.int32)
+    extra = {
+        "cu_seqlens_q": cu,
+        "cu_seqlens_k": cu,
+        "max_seqlen_q": 5,
+        "max_seqlen_k": 5,
+        # no laser_input_scale → no pre-scaling
+    }
+
+    out = impl._forward_prefix_kv_slice_npu(q, q, q, extra)
+
+    torch.testing.assert_close(captured["query"], q)
+    assert captured["scale"] == pytest.approx(0.5)
+    torch.testing.assert_close(out, torch.ones(1, 8, 2, 4))
+
+
 if __name__ == "__main__":
     print("Running FlashAttention Padding Tests...")
     print("=" * 60)

tests/diffusion/attention/test_rainfusion_plan.py

@@ -5,10 +5,9 @@
 
 The grids here are the ones MiniMax-H3 FL2VA actually produces for an 8.7s clip:
 1280x768 gives a 62x24x40 latent grid whose 59520 video rows land on the 128-row
-kernel block, and 1344x768 gives 62x24x42 whose 62496 rows straddle it. Only the
+kernel block, and 1344x768 gives 62x24x42 whose 62496 rows do not. Both are
-first can run sparse: rf_v2 tiles the sequence as a whole but pools its block
+handed to MindIE-SD: its rf_v2 preprocessing promotes an irregular video tail
-mask from the video and prefix segments separately, so the two only agree on the
+to the always-kept prefix segment before generating the block mask.
-block count when the video segment ends on a boundary.
 """
 
 import dataclasses
@@ -57,10 +56,13 @@ def test_block_aligned_video_segment_runs_sparse():
     assert plan.latent_shape == list(ALIGNED_GRID)
 
 
-def test_misaligned_video_segment_stays_dense():
+def test_misaligned_video_segment_runs_sparse_with_updated_mindiesd():
-    # Realigning the sequence would mean padding it, and rf_v2 ignores attn_mask:
+    plan = make_impl()._resolve_plan(make_metadata(MISALIGNED_GRID))
-    # pad keys would take a share of every real query's softmax denominator.
+
-    assert make_impl()._resolve_plan(make_metadata(MISALIGNED_GRID)) is None
+    assert plan is not None
+    assert plan.prefix_len == PREFIX_ROWS
+    assert plan.used_len == PREFIX_ROWS + 62496
+    assert plan.latent_shape == list(MISALIGNED_GRID)
 
 
 @pytest.mark.parametrize("prefix_len", [1, 127, _BLOCK_SIZE, 710, 900])
@@ -155,3 +157,28 @@ def test_fully_populated_mask_reproduces_dense_attention():
     ).transpose(1, 2)
     error = (out.float() - reference.float()).abs().mean() / reference.float().abs().mean()
     assert error < 2e-3, f"mean relative error {error:.4%} against dense attention"
+
+
+@pytest.mark.skipif(not current_omni_platform.is_npu(), reason="rf_v2 runs on Ascend NPU only.")
+def test_irregular_video_tail_reproduces_dense_attention_with_updated_mindiesd():
+    """vLLM forwards the full irregular grid; MindIE-SD owns its tail handling."""
+    torch.manual_seed(1)
+    prefix_len, grid = 384, (4, 16, 10)
+    video_len = grid[0] * grid[1] * grid[2]
+    used = prefix_len + video_len
+    heads, head_dim = 4, 128
+    q, k, v = (torch.randn(1, used, heads, head_dim, dtype=torch.bfloat16, device="npu") for _ in range(3))
+
+    impl = make_impl()
+    impl.rainfusion = dataclasses.replace(impl.rainfusion, sparsity=0.0)
+    plan = RainFusionPlan(prefix_len=prefix_len, used_len=used, latent_shape=list(grid))
+    out = impl._forward_sparse_npu(q, k, v, plan)
+
+    reference = torch.nn.functional.scaled_dot_product_attention(
+        q.transpose(1, 2),
+        k.transpose(1, 2),
+        v.transpose(1, 2),
+        scale=impl.softmax_scale,
+    ).transpose(1, 2)
+    error = (out.float() - reference.float()).abs().mean() / reference.float().abs().mean()
+    assert error < 2e-3, f"mean relative error {error:.4%} against dense attention"

tests/diffusion/cache/test_teacache_extractors.py

@@ -488,6 +488,14 @@ class _MiniMaxH3FakeAttention(nn.Module):
     class FakeBackend:
         supports_prefix_kv_slicing = False
 
+        # Mirror AttentionBackend.supports_packed_mask_free: H3's packed
+        # attention path calls attn_backend.supports_packed_mask_free() to decide
+        # whether to build the padding mask. Return False so the fake exercises
+        # the masked path (the abstract backend default).
+        @classmethod
+        def supports_packed_mask_free(cls) -> bool:
+            return False
+
     def __init__(self, **kwargs):
         del kwargs
         super().__init__()

tests/diffusion/distributed/test_qwenimage_spatial_shard.py

@@ -0,0 +1,233 @@
+import os
+from dataclasses import dataclass
+
+import pytest
+import torch
+import torch.distributed as dist
+import torch.multiprocessing as mp
+from diffusers.models.autoencoders.autoencoder_kl_qwenimage import QwenImageCausalConv3d
+
+from tests.helpers.mark import hardware_test
+from tests.helpers.runtime import get_open_port
+from vllm_omni.diffusion.distributed.autoencoders import qwenimage_spatial_shard
+from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_qwenimage import (
+    DistributedAutoencoderKLQwenImage,
+)
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import (
+    prepare_pipeline_spatial_shard_decode,
+)
+from vllm_omni.diffusion.offloader.module_collector import PipelineModules
+from vllm_omni.platforms import current_omni_platform
+
+
+@dataclass
+class _FakeExecutor:
+    group: object
+    parallel_size: int
+    parallel_mode: str
+
+
+def _tiny_qwenimage_vae() -> DistributedAutoencoderKLQwenImage:
+    return DistributedAutoencoderKLQwenImage(
+        base_dim=8,
+        z_dim=4,
+        dim_mult=[1, 2, 2, 2],
+        num_res_blocks=1,
+        attn_scales=[],
+        temperal_downsample=[False, True, True],
+        input_channels=3,
+        latents_mean=[0.0] * 4,
+        latents_std=[1.0] * 4,
+    )
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+def test_qwenimage_auto_spatial_shard_gate_is_shape_and_topology_aware(monkeypatch: pytest.MonkeyPatch):
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.distributed.autoencoders.spatial_shard.dist.get_world_size",
+        lambda group=None: 4,
+    )
+    vae = DistributedAutoencoderKLQwenImage.__new__(DistributedAutoencoderKLQwenImage)
+    vae.use_tiling = True
+    vae.distributed_executor = _FakeExecutor(group=object(), parallel_size=4, parallel_mode="auto")
+    vae.is_distributed_enabled = lambda: True
+
+    landscape = torch.zeros((1, 16, 1, 60, 104))
+    portrait = torch.zeros((1, 16, 1, 104, 60))
+
+    assert vae._spatial_shard_decode_split_dim(landscape, 4) == "width"
+    assert vae._spatial_shard_decode_split_dim(portrait, 4) == "height"
+    assert vae._spatial_shard_decode_enabled(landscape) is True
+
+    vae.distributed_executor.parallel_size = 2
+    assert vae._spatial_shard_decode_enabled(landscape) is False
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+def test_pipeline_dispatches_qwenimage_spatial_preparation(monkeypatch: pytest.MonkeyPatch):
+    vae = DistributedAutoencoderKLQwenImage.__new__(DistributedAutoencoderKLQwenImage)
+    prepared = []
+    vae._prepare_spatial_shard_decode = lambda: prepared.append(vae)
+
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.offloader.module_collector.ModuleDiscovery.discover",
+        lambda pipeline: PipelineModules(
+            dits=[],
+            dit_names=[],
+            encoders=[],
+            encoder_names=[],
+            vaes=[torch.nn.Identity(), vae],
+        ),
+    )
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.distributed.autoencoders.spatial_shard.dist.is_initialized",
+        lambda: True,
+    )
+
+    prepare_pipeline_spatial_shard_decode(torch.nn.Identity())
+
+    assert prepared == [vae]
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+@torch.no_grad()
+def test_qwenimage_installed_decoder_preserves_cache_discovery_state_and_direct_path():
+    torch.manual_seed(0)
+    vae = _tiny_qwenimage_vae().eval()
+    latents = torch.randn(1, 4, 2, 4, 5)
+    parameter_names = {name for name, _ in vae.named_parameters()}
+    state_dict = {name: value.clone() for name, value in vae.state_dict().items()}
+    reference = vae.decode(latents, return_dict=False)[0]
+    causal_conv_count = sum(isinstance(module, QwenImageCausalConv3d) for module in vae.decoder.modules())
+
+    qwenimage_spatial_shard.install_qwenimage_spatial_shard_decode(vae, group=object(), split_dim="height")
+    qwenimage_spatial_shard.install_qwenimage_spatial_shard_decode(vae, group=object(), split_dim="width")
+    vae.clear_cache()
+
+    assert causal_conv_count > 0
+    assert len(vae._feat_map) == causal_conv_count
+    assert sum(isinstance(module, QwenImageCausalConv3d) for module in vae.decoder.modules()) == causal_conv_count
+    assert any(
+        isinstance(module, qwenimage_spatial_shard.QwenImageDistCausalConv3d) for module in vae.decoder.modules()
+    )
+    assert {name for name, _ in vae.named_parameters()} == parameter_names
+    vae.load_state_dict(state_dict, strict=True)
+    assert torch.equal(vae.decode(latents, return_dict=False)[0], reference)
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+@torch.no_grad()
+def test_qwenimage_installed_decoder_direct_path_can_be_compiled():
+    torch.manual_seed(1)
+    vae = _tiny_qwenimage_vae().eval()
+    latents = torch.randn(1, 4, 1, 3, 5)
+    qwenimage_spatial_shard.install_qwenimage_spatial_shard_decode(vae, group=object())
+    eager = vae.decode(latents, return_dict=False)[0]
+
+    compiled_decode = torch.compile(vae.decode, backend="eager", fullgraph=False)
+    compiled = compiled_decode(latents, return_dict=False)[0]
+
+    torch.testing.assert_close(compiled, eager, rtol=0, atol=0)
+
+
+def _qwenimage_spatial_shard_worker(rank: int, master_port: str, results) -> None:
+    from vllm_omni.diffusion.distributed.parallel_state import (
+        destroy_model_parallel,
+        init_distributed_environment,
+        initialize_model_parallel,
+    )
+
+    os.environ["MASTER_ADDR"] = "127.0.0.1"
+    os.environ["MASTER_PORT"] = master_port
+    device = current_omni_platform.get_torch_device(rank)
+    current_omni_platform.set_device(device)
+    backend = current_omni_platform.dist_backend
+    init_distributed_environment(world_size=2, rank=rank, local_rank=rank, backend=backend)
+    initialize_model_parallel(sequence_parallel_size=2, ulysses_degree=2, backend=backend)
+
+    try:
+        torch.manual_seed(2)
+        vae = _tiny_qwenimage_vae().to(device=device, dtype=torch.float32).eval()
+        vae.init_distributed()
+        generator = torch.Generator(device=device).manual_seed(3)
+        landscape = torch.randn((1, 4, 2, 5, 7), generator=generator, device=device)
+        portrait = torch.randn((1, 4, 2, 7, 5), generator=generator, device=device)
+
+        with torch.inference_mode():
+            vae.use_tiling = False
+            vae.set_parallel_size(1, mode="tile")
+            landscape_reference = vae.decode(landscape, return_dict=False)[0]
+            portrait_reference = vae.decode(portrait, return_dict=False)[0]
+
+            vae.enable_tiling(
+                tile_sample_min_height=32,
+                tile_sample_min_width=32,
+                tile_sample_stride_height=24,
+                tile_sample_stride_width=24,
+            )
+            vae.set_parallel_size(2, mode="tile")
+            tile_before_install = vae.decode(landscape, return_dict=False)[0]
+
+            vae.set_parallel_size(2, mode="auto")
+            assert vae._spatial_shard_decode_split_dim(landscape, 2) == "width"
+            landscape_auto = vae.decode(landscape, return_dict=False)[0]
+            assert vae._spatial_shard_decode_split_dim(portrait, 2) == "height"
+            portrait_auto = vae.decode(portrait).sample
+
+            vae.set_parallel_size(2, mode="spatial_shard_height")
+            landscape_height = vae.decode(landscape, return_dict=False)[0]
+            vae.set_parallel_size(2, mode="spatial_shard_width")
+            portrait_width = vae.decode(portrait, return_dict=False)[0]
+
+            vae.set_parallel_size(2, mode="tile")
+            tile_after_install = vae.decode(landscape, return_dict=False)[0]
+
+        assert tile_after_install.shape == tile_before_install.shape
+        assert torch.equal(tile_after_install, tile_before_install)
+        assert all(
+            buffer is None
+            for module in vae.decoder.modules()
+            for name, buffer in module._buffers.items()
+            if name in {"_halo_recv_top_buf", "_halo_recv_bottom_buf"}
+        )
+
+        diffs = {
+            "landscape_auto": (landscape_auto - landscape_reference).abs().max().item(),
+            "portrait_auto": (portrait_auto - portrait_reference).abs().max().item(),
+            "landscape_height": (landscape_height - landscape_reference).abs().max().item(),
+            "portrait_width": (portrait_width - portrait_reference).abs().max().item(),
+        }
+        results[rank] = {
+            "diffs": diffs,
+            "landscape_shape": tuple(landscape_auto.shape),
+            "portrait_shape": tuple(portrait_auto.shape),
+        }
+    finally:
+        destroy_model_parallel()
+        if dist.is_initialized():
+            dist.destroy_process_group()
+
+
+@pytest.mark.core_model
+@pytest.mark.diffusion
+@pytest.mark.parallel
+@hardware_test(res={"cuda": "L4"}, num_cards=2)
+def test_qwenimage_spatial_shard_matches_reference_broadcasts_and_switches_paths():
+    manager = mp.get_context("spawn").Manager()
+    results = manager.dict()
+    mp.spawn(
+        _qwenimage_spatial_shard_worker,
+        args=(str(get_open_port()), results),
+        nprocs=2,
+        join=True,
+    )
+
+    assert set(results) == {0, 1}
+    assert results[0]["landscape_shape"] == results[1]["landscape_shape"] == (1, 3, 5, 40, 56)
+    assert results[0]["portrait_shape"] == results[1]["portrait_shape"] == (1, 3, 5, 56, 40)
+    for rank_results in results.values():
+        assert max(rank_results["diffs"].values()) <= 2e-5

tests/diffusion/distributed/test_wan_spatial_shard.py

@@ -1,4 +1,5 @@
 import os
+from contextlib import contextmanager
 from types import SimpleNamespace
 
 import pytest
@@ -10,6 +11,8 @@ from tests.helpers.mark import hardware_test
 from vllm_omni.diffusion.distributed.autoencoders import wan_spatial_shard
 from vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan import (
     DistributedAutoencoderKLWan,
+    prepare_pipeline_wan_spatial_shard_decode,
+    select_auto_spatial_shard_split_dim,
 )
 from vllm_omni.platforms import current_omni_platform
 
@@ -17,6 +20,23 @@ from vllm_omni.platforms import current_omni_platform
 # the end uses hardware_test (H100 x2) plus full_model / diffusion / parallel.
 
 
+@contextmanager
+def _active_spatial_shard(split_dim: str):
+    token = wan_spatial_shard._SPATIAL_SHARD_CONTEXT.set(
+        wan_spatial_shard.SpatialShardContext(
+            input_extent=2,
+            local_input_extent=2,
+            split_dim=split_dim,
+            rank=0,
+            world_size=3,
+        )
+    )
+    try:
+        yield
+    finally:
+        wan_spatial_shard._SPATIAL_SHARD_CONTEXT.reset(token)
+
+
 @pytest.mark.core_model
 @pytest.mark.cpu
 def test_split_for_parallel_decode_pads_uneven_height():
@@ -255,11 +275,13 @@ def test_dist_zero_pad_only_applies_global_height_edges(monkeypatch: pytest.Monk
 
     monkeypatch.setattr(wan_spatial_shard, "_rank_world", lambda group: (1, 3))
     mid_rank_pad = wan_spatial_shard.WanDistZeroPad2d((0, 1, 1, 1), group=object())
+    with _active_spatial_shard("height"):
         mid = mid_rank_pad(x)
     assert mid.shape == (1, 1, 2, 3)
 
     monkeypatch.setattr(wan_spatial_shard, "_rank_world", lambda group: (2, 3))
     last_rank_pad = wan_spatial_shard.WanDistZeroPad2d((0, 1, 1, 1), group=object())
+    with _active_spatial_shard("height"):
         last = last_rank_pad(x)
     assert last.shape == (1, 1, 3, 3)
 
@@ -270,12 +292,14 @@ def test_dist_zero_pad_only_applies_global_width_edges(monkeypatch: pytest.Monke
     x = torch.ones((1, 1, 2, 2))
 
     monkeypatch.setattr(wan_spatial_shard, "_rank_world", lambda group: (1, 3))
-    mid_rank_pad = wan_spatial_shard.WanDistZeroPad2d((1, 1, 0, 0), group=object(), split_dim="width")
+    mid_rank_pad = wan_spatial_shard.WanDistZeroPad2d((1, 1, 0, 0), group=object())
+    with _active_spatial_shard("width"):
         mid = mid_rank_pad(x)
     assert mid.shape == (1, 1, 2, 2)
 
     monkeypatch.setattr(wan_spatial_shard, "_rank_world", lambda group: (2, 3))
-    last_rank_pad = wan_spatial_shard.WanDistZeroPad2d((1, 1, 0, 0), group=object(), split_dim="width")
+    last_rank_pad = wan_spatial_shard.WanDistZeroPad2d((1, 1, 0, 0), group=object())
+    with _active_spatial_shard("width"):
         last = last_rank_pad(x)
     assert last.shape == (1, 1, 2, 3)
 
@@ -299,6 +323,113 @@ def test_spatial_shard_height_gate_falls_back_for_partial_group(monkeypatch: pyt
     assert vae._spatial_shard_decode_enabled(z) is False
 
 
+@pytest.mark.core_model
+@pytest.mark.cpu
+@pytest.mark.parametrize(
+    "z_shape,world_size,expected",
+    [
+        ((1, 16, 1, 60, 104), 4, "width"),
+        ((1, 16, 5, 60, 104), 4, "width"),
+        ((1, 16, 5, 104, 60), 4, "height"),
+        ((1, 16, 5, 2, 2), 4, None),
+        ((1, 16, 5, 64, 64), 4, "width"),
+    ],
+)
+def test_auto_spatial_shard_selector_is_shape_aware(z_shape, world_size, expected):
+    assert select_auto_spatial_shard_split_dim(z_shape, world_size) == expected
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+def test_auto_spatial_shard_gate_requires_full_group(monkeypatch: pytest.MonkeyPatch):
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan.dist.get_world_size",
+        lambda group=None: 4,
+    )
+
+    vae = DistributedAutoencoderKLWan.__new__(DistributedAutoencoderKLWan)
+    vae.use_tiling = True
+    vae.distributed_executor = SimpleNamespace(group=object(), parallel_size=4, parallel_mode="auto")
+    vae.is_distributed_enabled = lambda: True
+    large = torch.zeros((1, 16, 5, 60, 104))
+    unshardable = torch.zeros((1, 16, 1, 2, 2))
+
+    assert vae._spatial_shard_decode_split_dim(large, 4) == "width"
+    assert vae._spatial_shard_decode_enabled(large) is True
+    assert vae._spatial_shard_decode_enabled(unshardable) is False
+
+    vae.distributed_executor.parallel_size = 2
+    assert vae._spatial_shard_decode_enabled(large) is False
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+def test_spatial_wrappers_are_prepared_only_for_a_full_group(monkeypatch: pytest.MonkeyPatch):
+    vae = DistributedAutoencoderKLWan.__new__(DistributedAutoencoderKLWan)
+    object.__setattr__(
+        vae,
+        "distributed_executor",
+        SimpleNamespace(group=object(), parallel_size=2, parallel_mode="auto"),
+    )
+    installed = []
+
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.offloader.module_collector.ModuleDiscovery.discover",
+        lambda pipeline: SimpleNamespace(vaes=[vae]),
+    )
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan.dist.is_initialized",
+        lambda: True,
+    )
+    monkeypatch.setattr(
+        "vllm_omni.diffusion.distributed.autoencoders.autoencoder_kl_wan.dist.get_world_size",
+        lambda group=None: 4,
+    )
+    monkeypatch.setattr(
+        wan_spatial_shard,
+        "install_wan_spatial_shard_decode",
+        lambda candidate, group, split_dim: installed.append((candidate, group, split_dim)),
+    )
+
+    prepare_pipeline_wan_spatial_shard_decode(torch.nn.Identity())
+    assert installed == []
+
+    vae.distributed_executor.parallel_size = 4
+    prepare_pipeline_wan_spatial_shard_decode(torch.nn.Identity())
+    assert installed == [(vae, vae.distributed_executor.group, "height")]
+
+
+@pytest.mark.core_model
+@pytest.mark.cpu
+@torch.no_grad()
+def test_installed_spatial_decoder_keeps_direct_fallback_and_can_change_axis():
+    vae = DistributedAutoencoderKLWan(
+        base_dim=8,
+        decoder_base_dim=8,
+        z_dim=4,
+        dim_mult=[1, 2],
+        num_res_blocks=1,
+        attn_scales=[],
+        temperal_downsample=[False],
+        latents_mean=[0.0] * 4,
+        latents_std=[1.0] * 4,
+        scale_factor_temporal=1,
+        scale_factor_spatial=2,
+    ).eval()
+    latents = torch.randn(1, 4, 1, 4, 5)
+    parameter_names = {name for name, _ in vae.named_parameters()}
+    state_dict = {name: value.clone() for name, value in vae.state_dict().items()}
+    reference = vae.decode(latents, return_dict=False)[0]
+
+    wan_spatial_shard.install_wan_spatial_shard_decode(vae, group=object(), split_dim="height")
+    assert any(getattr(module, "_vllm_omni_dynamic_spatial_shard_conv", False) for module in vae.decoder.modules())
+    wan_spatial_shard.install_wan_spatial_shard_decode(vae, group=object(), split_dim="width")
+
+    assert {name for name, _ in vae.named_parameters()} == parameter_names
+    vae.load_state_dict(state_dict, strict=True)
+    assert torch.equal(vae.decode(latents, return_dict=False)[0], reference)
+
+
 @pytest.mark.core_model
 @pytest.mark.cpu
 def test_spatial_shard_width_gate_selects_width(monkeypatch: pytest.MonkeyPatch):
@@ -444,3 +575,99 @@ def test_spatial_shard_decode_matches_reference(split_dim: str):
     assert mean_abs_diff <= _SPATIAL_SHARD_TOLERANCE, (
         f"spatial_shard_{split_dim} mean_abs_diff {mean_abs_diff} exceeds {_SPATIAL_SHARD_TOLERANCE}"
     )
+
+
+def _auto_spatial_shard_decode_worker(rank: int, return_dict, master_port: str) -> None:
+    from vllm_omni.diffusion.distributed.parallel_state import (
+        destroy_model_parallel,
+        init_distributed_environment,
+        initialize_model_parallel,
+    )
+
+    os.environ["MASTER_ADDR"] = "127.0.0.1"
+    os.environ["MASTER_PORT"] = master_port
+    device = current_omni_platform.get_torch_device(rank)
+    current_omni_platform.set_device(device)
+    backend = current_omni_platform.dist_backend
+    init_distributed_environment(world_size=2, rank=rank, local_rank=rank, backend=backend)
+    initialize_model_parallel(sequence_parallel_size=2, ulysses_degree=2, backend=backend)
+
+    try:
+        vae = DistributedAutoencoderKLWan.from_pretrained(
+            _SPATIAL_SHARD_MODEL,
+            subfolder=_SPATIAL_SHARD_SUBFOLDER,
+            torch_dtype=torch.float32,
+        ).to(device=device, dtype=torch.float32)
+        vae.eval()
+        generator = torch.Generator(device=device).manual_seed(1)
+        small = torch.randn((1, vae.config.z_dim, 1, 60, 104), generator=generator, device=device)
+        landscape = torch.randn((1, vae.config.z_dim, 2, 60, 104), generator=generator, device=device)
+        portrait = torch.randn((1, vae.config.z_dim, 2, 104, 60), generator=generator, device=device)
+
+        with torch.inference_mode():
+            vae.use_tiling = False
+            vae.set_parallel_size(1, mode="tile")
+            small_reference = vae.decode(small, return_dict=False)[0]
+
+            vae.use_tiling = True
+            vae.set_parallel_size(2, mode="tile")
+            tile_before_install = vae.decode(small, return_dict=False)[0]
+
+            vae.set_parallel_size(2, mode="auto")
+            assert vae._spatial_shard_decode_split_dim(small, 2) == "width"
+            small_sharded = vae.decode(small, return_dict=False)[0]
+            assert vae._spatial_shard_decode_split_dim(landscape, 2) == "width"
+            vae.decode(landscape, return_dict=False)
+
+            vae.set_parallel_size(2, mode="tile")
+            tile_after_install = vae.decode(small, return_dict=False)[0]
+
+            vae.use_tiling = False
+            vae.set_parallel_size(1, mode="tile")
+            portrait_reference = vae.decode(portrait, return_dict=False)[0]
+
+            vae.use_tiling = True
+            vae.set_parallel_size(2, mode="auto")
+            assert vae._spatial_shard_decode_split_dim(portrait, 2) == "height"
+            portrait_sharded = vae.decode(portrait, return_dict=False)[0]
+
+        assert all(
+            buffer is None
+            for module in vae.decoder.modules()
+            for name, buffer in module._buffers.items()
+            if name in {"_halo_recv_top_buf", "_halo_recv_bottom_buf"}
+        )
+
+        if rank == 0:
+            small_diff = (small_sharded.float() - small_reference.float()).abs()
+            portrait_diff = (portrait_sharded.float() - portrait_reference.float()).abs()
+            return_dict["tile_fallback_exact"] = torch.equal(tile_after_install, tile_before_install)
+            return_dict["small_max_abs_diff"] = small_diff.max().item()
+            return_dict["small_mean_abs_diff"] = small_diff.mean().item()
+            return_dict["portrait_max_abs_diff"] = portrait_diff.max().item()
+            return_dict["portrait_mean_abs_diff"] = portrait_diff.mean().item()
+    finally:
+        destroy_model_parallel()
+        if dist.is_initialized():
+            dist.destroy_process_group()
+
+
+@pytest.mark.full_model
+@pytest.mark.diffusion
+@pytest.mark.parallel
+@hardware_test(res={"cuda": "H100"}, num_cards=2)
+def test_auto_spatial_shard_switches_shape_paths_safely():
+    manager = mp.get_context("spawn").Manager()
+    return_dict = manager.dict()
+    mp.spawn(
+        _auto_spatial_shard_decode_worker,
+        args=(return_dict, "29502"),
+        nprocs=2,
+        join=True,
+    )
+
+    assert return_dict.get("tile_fallback_exact") is True
+    assert return_dict["small_max_abs_diff"] <= _SPATIAL_SHARD_TOLERANCE
+    assert return_dict["small_mean_abs_diff"] <= _SPATIAL_SHARD_TOLERANCE
+    assert return_dict["portrait_max_abs_diff"] <= _SPATIAL_SHARD_TOLERANCE
+    assert return_dict["portrait_mean_abs_diff"] <= _SPATIAL_SHARD_TOLERANCE

tests/diffusion/models/minimax_h3/test_minimax_h3_contract.py

@@ -492,6 +492,10 @@ def test_cudnn_packed_attention_uses_python_length_without_padding_mask():
     class FakeBackend:
         supports_prefix_kv_slicing = True
 
+        @classmethod
+        def supports_packed_mask_free(cls) -> bool:
+            return False
+
     class FakeAttention(torch.nn.Module):
         attn_backend = FakeBackend
 
@@ -526,6 +530,48 @@ def test_cudnn_packed_attention_uses_python_length_without_padding_mask():
     assert attention.attention.metadata.extra["valid_kv_length"] == 5
 
 
+def test_packed_attention_skips_mask_for_packed_mask_free_backend():
+    from vllm_omni.diffusion.models.minimax_h3.minimax_h3_transformer import (
+        MiniMaxH3Attention,
+    )
+
+    class FakeBackend:
+        supports_prefix_kv_slicing = False
+
+        @classmethod
+        def supports_packed_mask_free(cls) -> bool:
+            return True
+
+    class FakeAttention(torch.nn.Module):
+        attn_backend = FakeBackend
+
+        def __init__(self):
+            super().__init__()
+            self.metadata = None
+
+        def forward(self, query, key, value, metadata):
+            self.metadata = metadata
+            return query
+
+    attention = object.__new__(MiniMaxH3Attention)
+    torch.nn.Module.__init__(attention)
+    attention.attention = FakeAttention()
+    q = torch.randn(8, 2, 4)
+
+    attention._run_packed_attention(
+        q,
+        q,
+        q,
+        cu_seqlens=torch.tensor([0, 5, 8], dtype=torch.int32),
+        max_seqlen=5,
+        packed_total=8,
+    )
+
+    assert attention.attention.metadata.attn_mask is None
+    assert attention.attention.metadata.extra["valid_kv_length"] == 5
+    assert attention.attention.metadata.extra["npu_attn_varlen"] is True
+
+
 def test_packed_attention_keeps_padding_mask_for_other_backends():
     from vllm_omni.diffusion.models.minimax_h3.minimax_h3_transformer import (
         MiniMaxH3Attention,
@@ -534,6 +580,10 @@ def test_packed_attention_keeps_padding_mask_for_other_backends():
     class FakeBackend:
         supports_prefix_kv_slicing = False
 
+        @classmethod
+        def supports_packed_mask_free(cls) -> bool:
+            return False
+
     class FakeAttention(torch.nn.Module):
         attn_backend = FakeBackend
 

tests/diffusion/models/minimax_h3/test_minimax_h3_parallel.py

@@ -69,6 +69,7 @@ def test_h3_fused_rope_matches_reference_and_preserves_unrotated_dims():
 
     attention = object.__new__(MiniMaxH3Attention)
     nn.Module.__init__(attention)
+    attention.rot_dim = 96
     attention.rope = RotaryEmbedding(is_neox_style=True, half_head_dim=False)
     attention.rope._forward_method = attention.rope.forward_native
 
@@ -119,3 +120,34 @@ def test_tp_accepts_checkpoint_supported_sizes():
     arch = MiniMaxH3DiTArchConfig()
     for tp_size in (1, 2, 4, 7):
         model._validate_tp_config(arch=arch, tp_size=tp_size)
+
+
+@pytest.mark.parametrize(("parallel_size", "enabled"), [(1, False), (2, True)])
+def test_video_vae_auto_mode_preserves_native_tile_parallelism(monkeypatch, parallel_size, enabled):
+    from vllm_omni.diffusion.models.minimax_h3 import vae as vae_module
+
+    parallel_state = {}
+    video_vae = object.__new__(vae_module.MiniMaxH3VideoVAE)
+    nn.Module.__init__(video_vae)
+    video_vae.remote = nn.Identity()
+    video_vae.model = type("FakeModel", (), {"parallel_tiling": False})()
+
+    monkeypatch.setattr(vae_module, "get_dit_group", lambda: object())
+    monkeypatch.setattr(vae_module.dist, "get_world_size", lambda group: 2)
+    monkeypatch.setattr(vae_module.dist, "get_rank", lambda group: 0)
+    monkeypatch.setattr(
+        vae_module.importlib,
+        "import_module",
+        lambda package: type(
+            "FakeParallelModule",
+            (),
+            {"get_parallel_state": staticmethod(lambda: parallel_state)},
+        )(),
+    )
+
+    video_vae.set_parallel_size(parallel_size, mode="auto")
+
+    assert video_vae.parallel_size == parallel_size
+    assert video_vae.model.parallel_tiling is enabled
+    assert parallel_state["group_size"] == parallel_size
+    assert parallel_state["sp_enabled"] is enabled

tests/diffusion/test_diffusion_model_runner.py

@@ -728,6 +728,19 @@ def test_execute_model_runs_forward_after_kv_receive(monkeypatch):
 @pytest.mark.core_model
 @pytest.mark.cpu
 def test_load_model_clears_cache_backend_for_unsupported_pipeline(monkeypatch):
+    memory_pool_active = False
+    preparation_pool_states = []
+
+    @contextmanager
+    def _memory_pool_context(tag):
+        nonlocal memory_pool_active
+        assert tag == "weights"
+        memory_pool_active = True
+        try:
+            yield
+        finally:
+            memory_pool_active = False
+
     class _DummyLoader:
         def __init__(self, load_config, od_config=None):
             del load_config, od_config
@@ -775,16 +788,22 @@ def test_load_model_clears_cache_backend_for_unsupported_pipeline(monkeypatch):
     monkeypatch.setattr(model_runner_module, "LoadConfig", lambda: object())
     monkeypatch.setattr(model_runner_module, "DiffusersPipelineLoader", _DummyLoader)
     monkeypatch.setattr(model_runner_module, "DeviceMemoryProfiler", _DummyMemoryProfiler)
+    monkeypatch.setattr(
+        model_runner_module,
+        "prepare_pipeline_spatial_shard_decode",
+        lambda pipeline: preparation_pool_states.append(memory_pool_active),
+    )
     monkeypatch.setattr(model_runner_module, "get_offload_backend", lambda od_config, device: None)
     monkeypatch.setattr(
         model_runner_module, "get_cache_backend", lambda cache_backend, cache_config: dummy_cache_backend
     )
 
-    DiffusionModelRunner.load_model(runner)
+    DiffusionModelRunner.load_model(runner, memory_pool_context_fn=_memory_pool_context)
 
     assert runner.cache_backend is None
     assert runner.od_config.cache_backend is None
     assert dummy_cache_backend.enabled is False
+    assert preparation_pool_states == [True]
 
 
 @pytest.mark.core_model

tests/docs/test_generate_examples.py

@@ -3,6 +3,7 @@
 
 import importlib.util
 from pathlib import Path
+from types import SimpleNamespace
 
 import pytest
 
@@ -43,3 +44,11 @@ def test_model_display_names_require_string_mapping(tmp_path, monkeypatch):
 
     with pytest.raises(ValueError, match="MODEL_DISPLAY_NAMES_FILE"):
         generate_examples.load_model_display_names()
+
+
+def test_only_general_serving_examples_get_generated_pages():
+    general_example = SimpleNamespace(category="offline_inference", path=Path("text_to_image"))
+    model_example = SimpleNamespace(category="offline_inference", path=Path("qwen3_omni"))
+
+    assert generate_examples.is_general_example(general_example)
+    assert not generate_examples.is_general_example(model_example)

tests/entrypoints/test_serve.py

@@ -76,6 +76,18 @@ def test_serve_parser_accepts_four_way_cfg_parallelism() -> None:
     assert args.cfg_parallel_size == 4
 
 
+def test_serve_parser_defaults_vae_parallel_mode_to_auto_and_accepts_tile() -> None:
+    parser = TrackingArgumentParser()
+    subparsers = parser.add_subparsers(dest="subcommand")
+    OmniServeCommand().subparser_init(subparsers)
+
+    default_args = parser.parse_args(["serve", "fake-model", "--omni"])
+    tile_args = parser.parse_args(["serve", "fake-model", "--omni", "--vae-parallel-mode", "tile"])
+
+    assert default_args.vae_parallel_mode == "auto"
+    assert tile_args.vae_parallel_mode == "tile"
+
+
 def _make_headless_args(**kwargs) -> TrackingNamespace:
     defaults = {
         "model": "fake-model",

tools/pre_commit/check_tts_adapter.py

@@ -123,18 +123,29 @@ def _legacy_detectors(tree: ast.AST) -> list[tuple[int, str]]:
     return found
 
 
-def _check(label: str, path: Path, actual: int, budget: int, sample: list[str], budget_name: str) -> list[str]:
+def _check(
+    label: str,
+    path: Path,
+    actual: int,
+    budget: int,
+    sample: list[str],
+    budget_name: str,
+    notices: list[str],
+) -> list[str]:
     if actual > budget:
         listing = "\n".join(f"      {line}" for line in sample)
         return [
             f"{path}: {actual} {label} exceeds the budget of {budget}.\n{listing}\n\n{_GUIDANCE}\n",
         ]
     if actual < budget:
-        return [
+        # Progress is never a build failure. Removing branches is the goal, so a
-            f"{path}: {actual} {label}, down from a budget of {budget}. "
+        # PR that does it must not hand-edit this file to stay green -- nor break
-            f"Lower {budget_name} to {actual} in {Path(__file__).relative_to(REPO_ROOT)} "
+        # `main` for everyone else when it merges from a stale base.
-            f"so the ratchet holds the new ground.",
+        notices.append(
-        ]
+            f"{path}: {actual} {label}, below the budget of {budget}. "
+            f"Lower {budget_name} to {actual} in "
+            f"{Path(__file__).relative_to(REPO_ROOT)} to hold the new ground."
+        )
     return []
 
 
@@ -152,6 +163,7 @@ def main(argv: list[str] | None = None) -> int:
             print(f"check_tts_adapter: expected file not found: {path}", file=sys.stderr)
             return 1
 
+    notices: list[str] = []
     branches = _model_type_branches(ast.parse(serving_path.read_text()))
     detectors = _legacy_detectors(ast.parse(adapters_path.read_text()))
 
@@ -162,6 +174,7 @@ def main(argv: list[str] | None = None) -> int:
         MAX_MODEL_TYPE_BRANCHES,
         [f"line {lineno}: {src}" for lineno, src in branches],
         "MAX_MODEL_TYPE_BRANCHES",
+        notices,
     )
     errors += _check(
         "unmigrated model types in LEGACY_TTS_DETECTORS",
@@ -170,8 +183,11 @@ def main(argv: list[str] | None = None) -> int:
         MAX_LEGACY_DETECTORS,
         [f"line {lineno}: {name}" for lineno, name in detectors],
         "MAX_LEGACY_DETECTORS",
+        notices,
     )
 
+    for notice in notices:
+        print(f"check_tts_adapter: {notice}", file=sys.stderr)
     for error in errors:
         print(f"check_tts_adapter: {error}", file=sys.stderr)
     return 1 if errors else 0

vllm_omni/config/omni_config.py

@@ -452,7 +452,7 @@ class OmniStageDiffusionParallelConfig(OmniStageParallelConfig):
     cfg_parallel_size: int = Field(default=1, ge=1)
     vae_patch_parallel_size: int = Field(default=1, ge=1)
     text_encoder_tp_size: int = Field(default=1, ge=1)
-    vae_parallel_mode: str = "tile"
+    vae_parallel_mode: str = "auto"
     use_hsdp: bool = False
     mask_sp_padding: bool = False
     hsdp_shard_size: int = -1
@@ -466,9 +466,10 @@ class OmniStageDiffusionParallelConfig(OmniStageParallelConfig):
             raise ValueError("allgather_degree > 1 is mutually exclusive with ulysses_degree/ring_degree > 1")
         if self.ulysses_mode not in {"strict", "advanced_uaa"}:
             raise ValueError("ulysses_mode must be 'strict' or 'advanced_uaa'")
-        if self.vae_parallel_mode not in {"tile", "spatial_shard_height", "spatial_shard_width"}:
+        if self.vae_parallel_mode not in {"auto", "tile", "spatial_shard_height", "spatial_shard_width"}:
             raise ValueError(
-                "vae_parallel_mode must be one of {'tile', 'spatial_shard_height', 'spatial_shard_width'}, "
+                "vae_parallel_mode must be one of "
+                "{'auto', 'tile', 'spatial_shard_height', 'spatial_shard_width'}, "
                 f"but got {self.vae_parallel_mode!r}."
             )
 

vllm_omni/diffusion/attention/backends/abstract.py

@@ -20,6 +20,17 @@ class AttentionBackend(ABC):
     # avoid a slower masked-attention plan when tail padding is not semantic.
     supports_prefix_kv_slicing: bool = False
 
+    @classmethod
+    def supports_packed_mask_free(cls) -> bool:
+        """Whether packed attention never reads attn_mask on this platform.
+
+        When True, models that pack a [real, pad] two-document layout and
+        carry cu_seqlens/max_seqlen in ``AttentionMetadata.extra`` may skip
+        constructing the padding mask entirely. Backends whose mask-free
+        behavior is platform-dependent must check current_omni_platform.
+        """
+        return False
+
     # ``OmniPlatformEnum`` values this backend runs on; None means unrestricted.
     # Platform resolution rejects an explicit selection outside this set, so a
     # hardware-specific backend fails before the model is built.
@@ -121,6 +132,17 @@ class AttentionMetadata:
     #     the packed cu_seqlens tensors.
     #   "valid_kv_length": int — contiguous valid K/V prefix length for a
     #     backend that advertises supports_prefix_kv_slicing.
+    #   "npu_attn_varlen": bool — model opt-in for the NPU packed varlen path
+    #     (TND npu_fusion_attention driven by cu_seqlens, mask never read).
+    #     Requires the [real, pad] two-document packing contract; see
+    #     FlashAttentionImpl._forward_varlen_packed_npu.
+    #   "laser_input_scale": float — model opt-in input pre-scale for the NPU
+    #     ascend_laser_attention path. The kernel stores unscaled QK^T in an
+    #     fp16 workspace, so outlier activations overflow 65504 into NaN rows;
+    #     with this set (>1), q/k/v are divided by the factor before the op,
+    #     the kernel scale_value is multiplied by its square, and the output
+    #     is scaled back (exact for power-of-two factors). Absent means no
+    #     pre-scaling. See FlashAttentionImpl._forward_prefix_kv_slice_npu.
 
     # Piecewise attention metadata (mixed causal/full masks).
     # full_attn_spans: per-sample [start, end) spans in global coordinates using full attention.

vllm_omni/diffusion/attention/backends/flash_attn.py

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
+import os
 from functools import partial
 
 import torch
@@ -16,6 +17,7 @@ from vllm_omni.diffusion.attention.backends.utils.piecewise_attn import (
     piecewise_attn,
 )
 from vllm_omni.diffusion.config import get_current_diffusion_config_or_none
+from vllm_omni.platforms import current_omni_platform
 
 logger = init_logger(__name__)
 
@@ -24,6 +26,15 @@ class FlashAttentionBackend(AttentionBackend):
     accept_output_buffer: bool = True
     supports_piecewise_spans: bool = True
 
+    @classmethod
+    def supports_packed_mask_free(cls) -> bool:
+        # CUDA: forward_cuda dispatches the packed cu_seqlens varlen path
+        # before ever reading attn_mask. NPU: forward_fa_npu honors the
+        # npu_attn_varlen opt-in and rebuilds the padding mask itself if the
+        # packed contract fails. XPU reads attn_mask, so models must keep
+        # constructing it there.
+        return current_omni_platform.is_cuda() or current_omni_platform.is_npu()
+
     @classmethod
     def supports_attention_mask(cls) -> bool:
         return True
@@ -415,7 +426,36 @@ class FlashAttentionImpl(AttentionImpl):
                 "For installation details, see https://gitcode.com/Ascend/MindIE-SD"
                 "Otherwise, use SDPA backend by setting DIFFUSION_ATTENTION_BACKEND=TORCH_SDPA"
             )
+        # Opt-in mask-free paths (mirror the CUDA cu_seqlens behavior): the
+        # model marks extra["npu_attn_varlen"] and carries packed metadata, so
+        # the padding document is excluded without reading or materializing
+        # the quadratic full_qk mask.
+        #   - default: packed varlen via mindiesd attention_forward_varlen;
+        #   - when MINDIE_SD_FA_TYPE=ascend_laser_attention: prefix K/V
+        #     slicing via mindiesd attention_forward (so the env-selected op
+        #     type is honored; the TND varlen op cannot be).
+        extra = attn_metadata.extra if attn_metadata else {}
+        if extra.get("npu_attn_varlen", False):
+            if os.environ.get("MINDIE_SD_FA_TYPE") == "ascend_laser_attention":
+                out = self._forward_prefix_kv_slice_npu(query, key, value, extra)
+            else:
+                out = self._forward_varlen_packed_npu(query, key, value, extra)
+            if out is not None:
+                return out
         attention_mask = attn_metadata.attn_mask if attn_metadata else None
+        if attention_mask is None and extra.get("npu_attn_varlen", False):
+            # Models skip mask construction when this opt-in is set
+            # (FlashAttentionBackend.supports_packed_mask_free). The packed
+            # paths above declined (contract mismatch), so rebuild the padding
+            # mask here to keep the masked fallback correct.
+            used = extra.get("valid_kv_length")
+            if not isinstance(used, int) or not 0 < used <= query.shape[1]:
+                raise ValueError(
+                    "npu_attn_varlen packed metadata is unusable and no attn_mask "
+                    f"was constructed (valid_kv_length={used!r}, seq_len={query.shape[1]}); "
+                    "refusing to run unmasked attention over padding rows."
+                )
+            attention_mask = torch.arange(query.shape[1], device=query.device)[None] < used
 
         # NPU aclnnFlashAttentionScore requires mask shape to be one of:
         # [B, N, Sq, Skv], [B, 1, Sq, Skv], [1, 1, Sq, Skv], or [Sq, Skv]
@@ -433,3 +473,161 @@ class FlashAttentionImpl(AttentionImpl):
             op_type="fused_attn_score",
             layout=layout,
         )
+
+    def _resolve_packed_seq_npu(
+        self,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        extra: dict,
+    ) -> tuple[list[int], list[int]] | None:
+        """Resolve packed document boundaries (cumulative end offsets per doc).
+
+        Returns (seq_q, seq_k), e.g. ([used_q, total_q], [used_k, total_k]),
+        or None unless the metadata matches the exact contract MiniMax-H3
+        produces:
+          - q/k/v are [1, T, N, D] (BSND, single packed batch);
+          - cu_seqlens describe a [real, pad] two-document packing, with the
+            padding document as a strict suffix;
+          - max_seqlen_q/k are Python ints equal to the real document length
+            (so boundaries are derived without any device sync).
+        """
+        if self.causal:
+            return None
+        packed_keys = ("cu_seqlens_q", "cu_seqlens_k", "max_seqlen_q", "max_seqlen_k")
+        if any(k not in extra for k in packed_keys):
+            return None
+        cu_q, cu_k = extra["cu_seqlens_q"], extra["cu_seqlens_k"]
+        used_q, used_k = extra["max_seqlen_q"], extra["max_seqlen_k"]
+        if query.shape[0] != 1 or key.shape[0] != 1:
+            return None
+        if not isinstance(used_q, int) or not isinstance(used_k, int):
+            return None
+        total_q, total_k = query.shape[1], key.shape[1]
+        # .shape is host-side metadata: counting documents never syncs.
+        if cu_q.shape[0] != cu_k.shape[0] or cu_q.shape[0] > 3:
+            return None
+        if not (0 < used_q <= total_q) or not (0 < used_k <= total_k):
+            return None
+        if used_q == total_q and used_k == total_k:
+            # No padding document: one full-length document.
+            return [total_q], [total_k]
+        if cu_q.shape[0] == 3 and used_q >= total_q - used_q and used_k >= total_k - used_k:
+            # [real, pad] packing: the real document must be the longer one
+            # (consistent with the max_seqlen naming).
+            return [used_q, total_q], [used_k, total_k]
+        return None
+
+    def _forward_varlen_packed_npu(
+        self,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        value: torch.Tensor,
+        extra: dict,
+    ) -> torch.Tensor | None:
+        """Packed varlen attention on NPU via mindiesd attention_forward_varlen.
+
+        Returns None (caller falls back to the mask path) when the packed
+        contract does not hold; see _resolve_packed_seq_npu.
+        """
+        resolved = self._resolve_packed_seq_npu(query, key, extra)
+        if resolved is None:
+            return None
+        seq_q, seq_k = resolved
+
+        try:
+            from mindiesd import attention_forward_varlen
+        except ImportError:
+            raise ImportError(
+                "FlashAttentionBackend NPU implementation requires MindIE-SD. "
+                "Please install MindIE-SD to enable NPU attention support. "
+                "For installation details, see https://gitcode.com/Ascend/MindIE-SD"
+                "Otherwise, use SDPA backend by setting DIFFUSION_ATTENTION_BACKEND=TORCH_SDPA"
+            )
+        q = query.squeeze(0)  # [T, N, D] == TND
+        k = key.squeeze(0)
+        v = value.squeeze(0)
+        # attention_forward_varlen wants cu_seqlens as host lists of cumulative
+        # offsets and forwards cu[1:] as actual_seq_qlen/actual_seq_kvlen.
+        out = attention_forward_varlen(
+            q,
+            k,
+            v,
+            [0, *seq_q],
+            [0, *seq_k],
+            softmax_scale=self.softmax_scale,
+        )
+        return out.unsqueeze(0)
+
+    def _forward_prefix_kv_slice_npu(
+        self,
+        query: torch.Tensor,
+        key: torch.Tensor,
+        value: torch.Tensor,
+        extra: dict,
+    ) -> torch.Tensor | None:
+        """Mask-free attention by slicing K/V to the valid prefix (zero-copy
+        views), then mindiesd attention_forward without a mask.
+
+        Same numerical contract as the varlen path: the padding document is a
+        strict suffix, so dropping it from K/V is identical to masking it out.
+        Query keeps full length; outputs on padding rows are never consumed
+        downstream. Returns None when the packed contract does not hold.
+
+        Used when MINDIE_SD_FA_TYPE=ascend_laser_attention: the TND varlen op
+        cannot honor the env-selected op type, while attention_forward can.
+
+        The laser kernel stores unscaled S=QK^T in an fp16 GM workspace, so
+        bf16 activations with large outliers overflow 65504 into ±inf and the
+        affected rows turn NaN. Models may opt into exact power-of-two input
+        pre-scaling via extra["laser_input_scale"] (see abstract.py): q/k/v
+        are divided by the factor, the kernel scale_value is multiplied by its
+        square, and the output is scaled back. Absent or invalid factor means
+        no pre-scaling.
+        """
+        resolved = self._resolve_packed_seq_npu(query, key, extra)
+        if resolved is None:
+            return None
+        _, seq_k = resolved
+        used_k = seq_k[0]  # real document length (first cumulative end)
+
+        try:
+            from mindiesd import attention_forward
+        except ImportError:
+            raise ImportError(
+                "FlashAttentionBackend NPU implementation requires MindIE-SD. "
+                "Please install MindIE-SD to enable NPU attention support. "
+                "For installation details, see https://gitcode.com/Ascend/MindIE-SD"
+                "Otherwise, use SDPA backend by setting DIFFUSION_ATTENTION_BACKEND=TORCH_SDPA"
+            )
+        # mindiesd always takes BSND input regardless of `layout`; the arg
+        # selects the op-internal layout and laser only supports BNSD, so do
+        # NOT forward the model's qkv_layout ("BSND" for MiniMax-H3) here.
+        layout = "BNSD"
+        key = key[:, :used_k]
+        value = value[:, :used_k]
+
+        input_scale = extra.get("laser_input_scale")
+        preserve_input_range = isinstance(input_scale, (int, float)) and input_scale > 1
+        if preserve_input_range:
+            query = query / input_scale
+            key = key / input_scale
+            value = value / input_scale
+        scale = self.softmax_scale
+        if preserve_input_range:
+            scale *= input_scale**2
+
+        def _postprocess(out: torch.Tensor) -> torch.Tensor:
+            return out * input_scale if preserve_input_range else out
+
+        return _postprocess(
+            attention_forward(
+                query,
+                key,
+                value,
+                attn_mask=None,
+                opt_mode="manual",
+                op_type="fused_attn_score",  # MINDIE_SD_FA_TYPE env overrides this
+                layout=layout,
+                scale=scale,
+            )
+        )

vllm_omni/diffusion/attention/backends/rainfusion_attn.py

@@ -128,9 +128,9 @@ class RainFusionAttentionImpl(AttentionImpl):
     whose extent the model publishes as ``AttentionMetadata.video_layout``. Every
     other case — warmup denoise steps, exempt layers, a layer that does not declare
     ``qkv_layout="BSND"``, sequences without a published video segment, video
-    segments too short to pay for block selection or not aligned to the kernel's
+    segments too short to pay for block selection — delegates to FlashAttention,
-    block size — delegates to FlashAttention, so a model can select this backend
+    so a model can select this backend unconditionally. MindIE-SD handles an
-    unconditionally.
+    irregular video tail internally, retaining it outside the sparse blocks.
     """
 
     def __init__(
@@ -292,25 +292,6 @@ class RainFusionAttentionImpl(AttentionImpl):
                 _MIN_VIDEO_BLOCKS,
             )
             return None
-        if video_len % _BLOCK_SIZE != 0:
-            # rf_v2 tiles the sequence into ceil((video + prefix) / 128) blocks but
-            # builds its block mask from the two segments pooled apart. The counts
-            # only agree when the video segment ends on a block boundary; otherwise
-            # a prefix block is forced on out of range, and the block straddling the
-            # seam holds real prefix rows that selection may drop. Padding the
-            # sequence to realign it is not an option because rf_v2 ignores
-            # attn_mask, so pad keys would take a share of every softmax denominator.
-            logger.warning_once(
-                "RAINFUSION_ATTN staying dense: latent grid %s gives %d video rows, which is not a "
-                "multiple of the %d-row kernel block. Choose a geometry whose latent_t * h * w is a "
-                "multiple of %d to enable sparsity.",
-                tuple(latent_shape),
-                video_len,
-                _BLOCK_SIZE,
-                _BLOCK_SIZE,
-            )
-            return None
-
         logger.info_once(
             "RAINFUSION_ATTN active: sparsity=%.2f, start_step=%d, exempt_layers=%d, "
             "latent_grid=%s, prefix_rows=%d, video_rows=%d. Realized sparsity is lower than nominal "

vllm_omni/diffusion/data.py

@@ -206,10 +206,13 @@ class DiffusionParallelConfig:
     process group.
     """
 
-    vae_parallel_mode: str = "tile"
+    vae_parallel_mode: str = "auto"
     """VAE parallel decode strategy.
 
-    - "tile": Patch/tile parallel decode (default). Each rank decodes a subset
+    - "auto": Select the longer spatial-shard axis for validated Wan and
+      distributed QwenImage tiled decodes on a full DiT-group topology;
+      otherwise use patch/tile parallel decode.
+    - "tile": Patch/tile parallel decode. Each rank decodes a subset
       of spatial tiles and the results are stitched on rank 0.
     - "spatial_shard_height": Spatially-sharded decode that splits decoder
       feature maps along height and exchanges halo rows around spatial
@@ -250,8 +253,9 @@ class DiffusionParallelConfig:
         assert self.allgather_degree > 0, "AllGather degree must be > 0"
         assert self.cfg_parallel_size > 0, "CFG parallel size must be > 0"
         assert self.vae_patch_parallel_size > 0, "VAE patch parallel size must be > 0"
-        assert self.vae_parallel_mode in {"tile", "spatial_shard_height", "spatial_shard_width"}, (
+        assert self.vae_parallel_mode in {"auto", "tile", "spatial_shard_height", "spatial_shard_width"}, (
-            "vae_parallel_mode must be one of {'tile', 'spatial_shard_height', 'spatial_shard_width'}, "
+            "vae_parallel_mode must be one of "
+            "{'auto', 'tile', 'spatial_shard_height', 'spatial_shard_width'}, "
             f"but got {self.vae_parallel_mode!r}."
         )
         if self.allgather_degree > 1:

vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py

@@ -4,16 +4,23 @@
 from typing import Any
 
 import torch
+import torch.distributed as dist
 from diffusers.models.autoencoders import AutoencoderKLQwenImage
 from diffusers.models.autoencoders.vae import DecoderOutput
 from vllm.logger import init_logger
 
+from vllm_omni.diffusion.distributed.autoencoders import qwenimage_spatial_shard
 from vllm_omni.diffusion.distributed.autoencoders.distributed_vae_executor import (
     DistributedOperator,
     DistributedVaeMixin,
     GridSpec,
     TileTask,
 )
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import (
+    prepare_spatial_shard_decode,
+    resolve_spatial_shard_split_dim,
+    spatial_shard_decode_enabled,
+)
 
 logger = init_logger(__name__)
 
@@ -104,10 +111,39 @@ class DistributedAutoencoderKLQwenImage(AutoencoderKLQwenImage, DistributedVaeMi
         ]
         return dec
 
+    def _spatial_shard_decode_split_dim(
+        self,
+        z: torch.Tensor | None = None,
+        world_size: int | None = None,
+    ) -> str | None:
+        return resolve_spatial_shard_split_dim(self.distributed_executor.parallel_mode, z, world_size)
+
+    def _spatial_shard_decode_enabled(self, z: torch.Tensor) -> bool:
+        return spatial_shard_decode_enabled(self, z, model_name="QwenImage")
+
+    def _prepare_spatial_shard_decode(self) -> None:
+        prepare_spatial_shard_decode(
+            self,
+            install=qwenimage_spatial_shard.install_qwenimage_spatial_shard_decode,
+        )
+
     def tiled_decode(self, z: torch.Tensor, return_dict: bool = True):
         if not self.is_distributed_enabled():
             return super().tiled_decode(z, return_dict=return_dict)
 
+        if self._spatial_shard_decode_enabled(z):
+            world_size = dist.get_world_size(group=self.distributed_executor.group)
+            split_dim = self._spatial_shard_decode_split_dim(z, world_size)
+            assert split_dim is not None
+            logger.debug("Decode running with QwenImage VAE spatial_shard_%s mode", split_dim)
+            return qwenimage_spatial_shard.spatial_shard_decode(
+                self,
+                z,
+                group=self.distributed_executor.group,
+                return_dict=return_dict,
+                split_dim=split_dim,
+            )
+
         logger.debug("Decode running with distributed executor")
         result = self.distributed_executor.execute(
             z,

vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_wan.py

@@ -18,11 +18,25 @@ from vllm_omni.diffusion.distributed.autoencoders.distributed_vae_executor impor
     GridSpec,
     TileTask,
 )
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import (
+    prepare_pipeline_spatial_shard_decode,
+    prepare_spatial_shard_decode,
+    resolve_spatial_shard_split_dim,
+    spatial_shard_decode_enabled,
+)
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import (
+    select_auto_spatial_shard_split_dim as select_auto_spatial_shard_split_dim,
+)
 from vllm_omni.platforms import current_omni_platform
 
 logger = init_logger(__name__)
 
 
+def prepare_pipeline_wan_spatial_shard_decode(pipeline: torch.nn.Module) -> None:
+    """Backward-compatible alias for the model-agnostic pipeline dispatcher."""
+    prepare_pipeline_spatial_shard_decode(pipeline)
+
+
 class OmniAutoencoderKLWan(AutoencoderKLWan):
     def _execution_context(self):
         try:
@@ -270,45 +284,30 @@ class DistributedAutoencoderKLWan(OmniAutoencoderKLWan, DistributedVaeMixin):
         dec = torch.clamp(dec, min=-1.0, max=1.0)
         return dec
 
-    def _spatial_shard_decode_split_dim(self) -> str | None:
+    def _spatial_shard_decode_split_dim(
-        mode = self.distributed_executor.parallel_mode
+        self,
-        if mode == "spatial_shard_width":
+        z: torch.Tensor | None = None,
-            return "width"
+        world_size: int | None = None,
-        if mode == "spatial_shard_height":
+    ) -> str | None:
-            return "height"
+        return resolve_spatial_shard_split_dim(self.distributed_executor.parallel_mode, z, world_size)
-        return None
 
     def _spatial_shard_decode_enabled(self, z: torch.Tensor) -> bool:
-        split_dim = self._spatial_shard_decode_split_dim()
+        return spatial_shard_decode_enabled(self, z, model_name="Wan")
-        if split_dim is None:
-            return False
-        if z.ndim != 5:
-            logger.warning("Wan VAE spatial sharded decode expects 5D latent input; falling back to tiled decode.")
-            return False
-        if not self.is_distributed_enabled():
-            return False
 
-        group = self.distributed_executor.group
+    def _prepare_spatial_shard_decode(self) -> None:
-        world_size = dist.get_world_size(group=group)
+        prepare_spatial_shard_decode(
-        requested_size = int(self.distributed_executor.parallel_size)
+            self,
-        if requested_size != world_size:
+            install=wan_spatial_shard.install_wan_spatial_shard_decode,
-            logger.warning(
-                "Wan VAE spatial sharded decode currently requires vae_patch_parallel_size "
-                "to match the DIT group size; falling back to tiled decode. "
-                "requested=%s dit_group=%s split_dim=%s",
-                requested_size,
-                world_size,
-                split_dim,
         )
-            return False
-        return True
 
     def tiled_decode(self, z: torch.Tensor, return_dict: bool = True):
         if not self.is_distributed_enabled():
             return super().tiled_decode(z, return_dict=return_dict)
 
         if self._spatial_shard_decode_enabled(z):
-            split_dim = self._spatial_shard_decode_split_dim()
+            world_size = dist.get_world_size(group=self.distributed_executor.group)
+            split_dim = self._spatial_shard_decode_split_dim(z, world_size)
+            assert split_dim is not None
             logger.debug("Decode running with Wan VAE spatial_shard_%s mode", split_dim)
             return wan_spatial_shard.spatial_shard_decode(
                 self,

vllm_omni/diffusion/distributed/autoencoders/qwenimage_spatial_shard.py

@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+"""QwenImage adapter for the shared spatial-shard VAE decoder kernels."""
+
+from __future__ import annotations
+
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+from diffusers.models.autoencoders.autoencoder_kl_qwenimage import QwenImageCausalConv3d
+from diffusers.models.autoencoders.vae import DecoderOutput
+
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import SpatialShardVAE
+from vllm_omni.diffusion.distributed.autoencoders.wan_spatial_shard import (
+    SpatialShardCausalConv3dMixin,
+    install_spatial_shard_decode,
+    spatial_shard_decode_impl,
+)
+
+
+class QwenImageDistCausalConv3d(SpatialShardCausalConv3dMixin, QwenImageCausalConv3d):
+    """Context-aware QwenImage causal conv that remains cache-discoverable."""
+
+    def __init__(self, source: nn.Conv3d, group: dist.ProcessGroup) -> None:
+        # Initialize Conv3d directly so the replacement preserves source device,
+        # dtype, groups, and bias while remaining an isinstance() match for
+        # QwenImageCausalConv3d. Diffusers clear_cache() relies on that match.
+        nn.Conv3d.__init__(
+            self,
+            source.in_channels,
+            source.out_channels,
+            source.kernel_size,
+            stride=source.stride,
+            padding=0,
+            dilation=source.dilation,
+            groups=source.groups,
+            bias=source.bias is not None,
+            padding_mode=source.padding_mode,
+            device=source.weight.device,
+            dtype=source.weight.dtype,
+        )
+        self._init_spatial_shard_causal_conv(source, group)
+
+    def forward(self, x: torch.Tensor, cache_x: torch.Tensor | None = None) -> torch.Tensor:
+        return self._spatial_shard_causal_conv_forward(x, cache_x)
+
+
+def install_qwenimage_spatial_shard_decode(
+    vae: SpatialShardVAE,
+    group: dist.ProcessGroup,
+    split_dim: str = "height",
+) -> None:
+    install_spatial_shard_decode(
+        vae,
+        group,
+        split_dim,
+        causal_conv_class_name="QwenImageCausalConv3d",
+        causal_conv_factory=QwenImageDistCausalConv3d,
+        attention_block_class_name="QwenImageAttentionBlock",
+        installed_attr="_vllm_omni_qwenimage_spatial_shard_installed",
+        model_name="QwenImage",
+    )
+
+
+def spatial_shard_decode(
+    vae: SpatialShardVAE,
+    z: torch.Tensor,
+    *,
+    group: dist.ProcessGroup,
+    return_dict: bool = True,
+    split_dim: str = "height",
+) -> DecoderOutput | tuple[torch.Tensor]:
+    """Decode QwenImage latents and preserve its all-rank output contract."""
+    return spatial_shard_decode_impl(
+        vae,
+        z,
+        group=group,
+        install=install_qwenimage_spatial_shard_decode,
+        model_name="QwenImage",
+        pass_first_chunk=False,
+        broadcast_result=True,
+        unpatchify_patch_size=None,
+        return_dict=return_dict,
+        split_dim=split_dim,
+    )

vllm_omni/diffusion/distributed/autoencoders/spatial_shard.py

@@ -0,0 +1,142 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import Protocol
+
+import torch
+import torch.distributed as dist
+from vllm.logger import init_logger
+
+logger = init_logger(__name__)
+
+
+class SpatialShardExecutor(Protocol):
+    group: dist.ProcessGroup
+    parallel_mode: str
+    parallel_size: int
+
+    def _sync_final_result(
+        self,
+        rank0_result: torch.Tensor,
+        output_ndim: int,
+        output_device: torch.device,
+        output_dtype: torch.dtype,
+    ) -> torch.Tensor: ...
+
+
+class SpatialShardVAE(Protocol):
+    distributed_executor: SpatialShardExecutor
+    decoder: torch.nn.Module
+    post_quant_conv: torch.nn.Module
+    dtype: torch.dtype
+    _conv_idx: list[int]
+    _feat_map: list[object]
+
+    def is_distributed_enabled(self) -> bool: ...
+
+    def clear_cache(self) -> None: ...
+
+
+def select_auto_spatial_shard_split_dim(
+    z_shape: tuple[int, ...],
+    world_size: int,
+) -> str | None:
+    """Select the longer spatial axis that can be split across every rank."""
+    if len(z_shape) != 5 or world_size <= 1:
+        return None
+
+    _, _, _, height, width = z_shape
+    candidates = [
+        (extent, split_dim) for extent, split_dim in ((height, "height"), (width, "width")) if extent >= world_size
+    ]
+    if not candidates:
+        return None
+    # Prefer width for square latents. It was modestly faster in the original
+    # four-GPU Wan benchmark and keeps the choice deterministic across models.
+    return max(candidates, key=lambda candidate: (candidate[0], candidate[1] == "width"))[1]
+
+
+def resolve_spatial_shard_split_dim(
+    mode: str,
+    z: torch.Tensor | None = None,
+    world_size: int | None = None,
+) -> str | None:
+    if mode == "spatial_shard_width":
+        return "width"
+    if mode == "spatial_shard_height":
+        return "height"
+    if mode == "auto" and z is not None and world_size is not None:
+        return select_auto_spatial_shard_split_dim(tuple(z.shape), world_size)
+    return None
+
+
+def spatial_shard_decode_enabled(vae: SpatialShardVAE, z: torch.Tensor, *, model_name: str) -> bool:
+    """Apply the shared request- and topology-level spatial decode policy."""
+    executor = vae.distributed_executor
+    if executor.parallel_mode == "tile":
+        return False
+    if z.ndim != 5:
+        logger.warning(
+            "%s VAE spatial sharded decode expects 5D latent input; falling back to tiled decode.", model_name
+        )
+        return False
+    if not vae.is_distributed_enabled():
+        return False
+
+    group = executor.group
+    world_size = dist.get_world_size(group=group)
+    requested_size = int(executor.parallel_size)
+    requested_split_dim = resolve_spatial_shard_split_dim(executor.parallel_mode)
+    if requested_size != world_size:
+        if executor.parallel_mode == "auto":
+            logger.debug(
+                "%s VAE auto decode selected tile mode for a partial DiT group (requested=%s dit_group=%s)",
+                model_name,
+                requested_size,
+                world_size,
+            )
+        elif requested_split_dim is not None:
+            logger.warning(
+                "%s VAE spatial sharded decode currently requires vae_patch_parallel_size "
+                "to match the DIT group size; falling back to tiled decode. "
+                "requested=%s dit_group=%s split_dim=%s",
+                model_name,
+                requested_size,
+                world_size,
+                requested_split_dim,
+            )
+        return False
+    return resolve_spatial_shard_split_dim(executor.parallel_mode, z, world_size) is not None
+
+
+def prepare_spatial_shard_decode(
+    vae: SpatialShardVAE,
+    *,
+    install: Callable[[SpatialShardVAE, dist.ProcessGroup, str], None],
+) -> None:
+    """Install one VAE's dynamic wrappers while allocations are still tagged."""
+    executor = vae.distributed_executor
+    mode = executor.parallel_mode
+    if mode not in {"auto", "spatial_shard_height", "spatial_shard_width"}:
+        return
+    requested_size = int(executor.parallel_size)
+    world_size = dist.get_world_size(group=executor.group)
+    if requested_size <= 1 or requested_size != world_size:
+        return
+    split_dim = "width" if mode == "spatial_shard_width" else "height"
+    install(vae, executor.group, split_dim)
+
+
+def prepare_pipeline_spatial_shard_decode(pipeline: torch.nn.Module) -> None:
+    """Prepare every VAE that advertises spatial-shard decode capability."""
+    from vllm_omni.diffusion.offloader.module_collector import ModuleDiscovery
+
+    if not dist.is_initialized():
+        return
+    for vae in ModuleDiscovery.discover(pipeline).vaes:
+        prepare = getattr(vae, "_prepare_spatial_shard_decode", None)
+        if callable(prepare):
+            prepare()

vllm_omni/diffusion/distributed/autoencoders/wan_spatial_shard.py

@@ -7,19 +7,21 @@
 #   (python/sglang/multimodal_gen/runtime/layers/parallel_conv.py)
 # which is in turn adapted from FastVideo (https://github.com/hao-ai-lab/FastVideo).
 # This version generalizes the height-only sharding to shard along height or
-# width and adds the Wan causal-conv ``feat_cache`` handling.
+# width and supports the causal-conv ``feat_cache`` handling used by Wan and
-"""Spatially-sharded Wan VAE decode.
+# QwenImage.
+"""Shared spatial-shard kernels plus the Wan VAE adapter.
 
-The existing distributed Wan VAE path shards *tiles*.  This module adds an
+The halo, padding, stride-trim, attention-gather, and decode-lifecycle helpers
-opt-in decode backend that shards decoder feature maps along height or width and
+are also reused by QwenImage's thin adapter. The backend shards decoder feature
-exchanges boundary rows/columns before spatial convolutions.  It is
+maps along height or width and exchanges boundary rows/columns before spatial
-intentionally decode-only and keeps checkpoint loading unchanged by patching the
+convolutions. It is decode-only and keeps checkpoint loading unchanged by
-already-loaded decoder.
+patching the already-loaded decoder.
 """
 
 from __future__ import annotations
 
 import math
+from collections.abc import Callable
 from contextlib import nullcontext
 from contextvars import ContextVar
 from dataclasses import dataclass
@@ -34,6 +36,8 @@ from diffusers.models.autoencoders.autoencoder_kl_wan import unpatchify
 from diffusers.models.autoencoders.vae import DecoderOutput
 from vllm.logger import init_logger
 
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import SpatialShardVAE
+
 logger = init_logger(__name__)
 
 
@@ -52,12 +56,17 @@ _SPATIAL_SHARD_CONTEXT: ContextVar[SpatialShardContext | None] = ContextVar(
 )
 
 
+def _active_spatial_shard_split_dim() -> str | None:
+    context = _SPATIAL_SHARD_CONTEXT.get()
+    return context.split_dim if context is not None else None
+
+
 def _spatial_dim(split_dim: str) -> int:
     if split_dim == "height":
         return -2
     if split_dim == "width":
         return -1
-    raise ValueError(f"Unsupported Wan VAE split_dim={split_dim!r}; expected 'height' or 'width'.")
+    raise ValueError(f"Unsupported VAE split_dim={split_dim!r}; expected 'height' or 'width'.")
 
 
 def _narrow_along_dim(x: torch.Tensor, dim: int, start: int, length: int) -> torch.Tensor:
@@ -155,9 +164,9 @@ def split_for_parallel_decode(
     rank = 0 if rank is None else int(rank)
     world_size = 1 if world_size is None else int(world_size)
     if world_size < 1:
-        raise ValueError(f"Wan VAE world_size must be >= 1, got {world_size}.")
+        raise ValueError(f"VAE world_size must be >= 1, got {world_size}.")
     if not 0 <= rank < world_size:
-        raise ValueError(f"Wan VAE rank must satisfy 0 <= rank < world_size, got rank={rank}, world_size={world_size}.")
+        raise ValueError(f"VAE rank must satisfy 0 <= rank < world_size, got rank={rank}, world_size={world_size}.")
 
     dim = _spatial_dim(split_dim)
     expected_extent = x.shape[dim] * (2**upsample_count)
@@ -323,21 +332,27 @@ class WanDistZeroPad2d(nn.Module):
         padding: tuple[int, int, int, int],
         group: dist.ProcessGroup,
         *,
-        split_dim: str = "height",
+        defer_split_after_padding: bool = False,
-        split_padding: tuple[int, int] | None = None,
     ) -> None:
         super().__init__()
         self.padding = padding
-        self.split_dim = split_dim
+        self.defer_split_after_padding = defer_split_after_padding
-        default_split_padding = (padding[2], padding[3]) if split_dim == "height" else (padding[0], padding[1])
-        self.split_padding = split_padding or default_split_padding
         self.group = group
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
+        split_dim = _active_spatial_shard_split_dim()
+        if split_dim is None:
+            return F.pad(x, self.padding)
+
         rank, world_size = _rank_world(self.group)
         left, right, top, bottom = self.padding
+        if self.defer_split_after_padding:
+            if split_dim == "height":
+                bottom = 0
+            else:
+                right = 0
         if world_size > 1:
-            if self.split_dim == "height":
+            if split_dim == "height":
                 top = top if rank == 0 else 0
                 bottom = bottom if rank == world_size - 1 else 0
             else:
@@ -351,8 +366,7 @@ class WanDistConv2d(nn.Conv2d):
         self,
         source: nn.Conv2d,
         group: dist.ProcessGroup,
-        split_dim: str = "height",
+        deferred_padding: tuple[int, int, int, int] | None = None,
-        split_padding: tuple[int, int] | None = None,
     ):
         super().__init__(
             source.in_channels,
@@ -369,176 +383,253 @@ class WanDistConv2d(nn.Conv2d):
         )
         self.load_state_dict(source.state_dict())
         self.group = group
-        self.split_dim = split_dim
+        self._direct_padding = source.padding
-        self.split_tensor_dim = _spatial_dim(split_dim)
+        self._direct_padding_mode = source.padding_mode
-        kernel_extent = self.kernel_size[-2] if split_dim == "height" else self.kernel_size[-1]
+        self._direct_reversed_padding = source._reversed_padding_repeated_twice
-        self.halo_size = (kernel_extent - 1) // 2
+        self._deferred_padding = deferred_padding
-        pad_h = source.padding[-2] if isinstance(source.padding, tuple) else source.padding
+        source_padding = source.padding if isinstance(source.padding, tuple) else (source.padding, source.padding)
-        pad_w = source.padding[-1] if isinstance(source.padding, tuple) else source.padding
+        if len(source_padding) != 2 or not all(isinstance(value, int) for value in source_padding):
-        if split_dim == "height":
+            raise ValueError(f"Spatial-shard Conv2d requires integer padding, got {source.padding!r}.")
-            if split_padding is None:
+        self._spatial_pad_h = int(source_padding[-2])
-                split_padding = (pad_h, pad_h)
+        self._spatial_pad_w = int(source_padding[-1])
-            self._non_split_padding = (pad_w, pad_w, 0, 0)
+        self.register_buffer("_halo_recv_top_buf", None, persistent=False)
-            self.kernel_extent = self.kernel_size[-2]
+        self.register_buffer("_halo_recv_bottom_buf", None, persistent=False)
-            self.stride_extent = self.stride[-2]
+        self._trim_cache: dict[tuple[str, int], tuple[int, int, int]] = {}
-        else:
-            if split_padding is None:
-                split_padding = (pad_w, pad_w)
-            self._non_split_padding = (0, 0, pad_h, pad_h)
-            self.kernel_extent = self.kernel_size[-1]
-            self.stride_extent = self.stride[-1]
-        self.split_pad_left, self.split_pad_right = split_padding
-        self._halo_recv_top_buf: torch.Tensor | None = None
-        self._halo_recv_bottom_buf: torch.Tensor | None = None
-        self._trim_cache: dict[int, tuple[int, int, int]] = {}
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
-        x = F.pad(x, self._non_split_padding)
+        split_dim = _active_spatial_shard_split_dim()
+        if split_dim is None:
+            if self._direct_padding_mode != "zeros":
+                x = F.pad(x, self._direct_reversed_padding, mode=self._direct_padding_mode)
+                padding: str | tuple[int, int] = (0, 0)
+            else:
+                padding = self._direct_padding
+            return F.conv2d(x, self.weight, self.bias, self.stride, padding, self.dilation, self.groups)
+
+        split_tensor_dim = _spatial_dim(split_dim)
+        if split_dim == "height":
+            kernel_extent = self.kernel_size[-2]
+            stride_extent = self.stride[-2]
+            non_split_padding = (self._spatial_pad_w, self._spatial_pad_w, 0, 0)
+            default_split_padding = (self._spatial_pad_h, self._spatial_pad_h)
+            deferred_split_padding = (
+                (self._deferred_padding[2], self._deferred_padding[3]) if self._deferred_padding is not None else None
+            )
+        else:
+            kernel_extent = self.kernel_size[-1]
+            stride_extent = self.stride[-1]
+            non_split_padding = (0, 0, self._spatial_pad_h, self._spatial_pad_h)
+            default_split_padding = (self._spatial_pad_w, self._spatial_pad_w)
+            deferred_split_padding = (
+                (self._deferred_padding[0], self._deferred_padding[1]) if self._deferred_padding is not None else None
+            )
+        split_pad_left, split_pad_right = deferred_split_padding or default_split_padding
+        halo_size = (kernel_extent - 1) // 2
+
+        x = F.pad(x, non_split_padding)
         x_padded, self._halo_recv_top_buf, self._halo_recv_bottom_buf = halo_exchange(
             x,
             group=self.group,
-            halo_size=self.halo_size,
+            halo_size=halo_size,
-            split_dim=self.split_dim,
+            split_dim=split_dim,
             recv_top_buf=self._halo_recv_top_buf,
             recv_bottom_buf=self._halo_recv_bottom_buf,
         )
-        shift, start, upper_bound = self._get_trim_params(x.shape[self.split_tensor_dim])
+        shift, start, upper_bound = self._get_trim_params(
+            x.shape[split_tensor_dim],
+            split_dim=split_dim,
+            halo_size=halo_size,
+            split_pad_left=split_pad_left,
+            split_pad_right=split_pad_right,
+            kernel_extent=kernel_extent,
+            stride_extent=stride_extent,
+        )
         if shift:
             x_padded = _narrow_along_dim(
                 x_padded,
-                self.split_tensor_dim,
+                split_tensor_dim,
                 shift,
-                x_padded.shape[self.split_tensor_dim] - shift,
+                x_padded.shape[split_tensor_dim] - shift,
             )
         out = super().forward(x_padded)
-        out = _trim_local_conv_output(out, self.halo_size, start, upper_bound, split_dim=self.split_dim)
+        out = _trim_local_conv_output(out, halo_size, start, upper_bound, split_dim=split_dim)
-        return _zero_invalid_extent(out, split_dim=self.split_dim)
+        return _zero_invalid_extent(out, split_dim=split_dim)
 
-    def _get_trim_params(self, local_extent: int) -> tuple[int, int, int]:
+    def _get_trim_params(
-        trim_params = self._trim_cache.get(local_extent)
+        self,
+        local_extent: int,
+        *,
+        split_dim: str,
+        halo_size: int,
+        split_pad_left: int,
+        split_pad_right: int,
+        kernel_extent: int,
+        stride_extent: int,
+    ) -> tuple[int, int, int]:
+        cache_key = (split_dim, local_extent)
+        trim_params = self._trim_cache.get(cache_key)
         if trim_params is None:
             rank, world_size = _rank_world(self.group)
             trim_params = _compute_conv_trim_params(
                 local_extent=local_extent,
                 rank=rank,
                 world_size=world_size,
-                halo_size=self.halo_size,
+                halo_size=halo_size,
-                pad_before=self.split_pad_left,
+                pad_before=split_pad_left,
-                pad_after=self.split_pad_right,
+                pad_after=split_pad_right,
-                kernel_extent=self.kernel_extent,
+                kernel_extent=kernel_extent,
-                stride_extent=self.stride_extent,
+                stride_extent=stride_extent,
             )
-            self._trim_cache[local_extent] = trim_params
+            self._trim_cache[cache_key] = trim_params
         return trim_params
 
 
-class WanDistCausalConv3d(nn.Conv3d):
+# Model-neutral aliases let other causal VAEs reuse the implementation while
-    def __init__(
+# preserving the original Wan class identities for stacked PRs and downstreams.
+SpatialShardZeroPad2d = WanDistZeroPad2d
+SpatialShardConv2d = WanDistConv2d
+
+
+class SpatialShardCausalConv3dMixin:
+    """Shared causal-convolution behavior for supported Diffusers VAE classes."""
+
+    def _init_spatial_shard_causal_conv(
         self,
         source: nn.Conv3d,
         group: dist.ProcessGroup,
-        split_dim: str = "height",
+    ) -> None:
-    ):
-        super().__init__(
-            source.in_channels,
-            source.out_channels,
-            source.kernel_size,
-            stride=source.stride,
-            padding=0,
-            dilation=source.dilation,
-            groups=source.groups,
-            bias=source.bias is not None,
-            padding_mode=source.padding_mode,
-            device=source.weight.device,
-            dtype=source.weight.dtype,
-        )
         self.load_state_dict(source.state_dict())
         self.group = group
-        self.split_dim = split_dim
-        self.split_tensor_dim = _spatial_dim(split_dim)
         source_padding = getattr(source, "_padding", None)
         if source_padding is None:
             p_t, p_h, p_w = source.padding
             source_padding = (p_w, p_w, p_h, p_h, 2 * p_t, 0)
         self._source_padding = tuple(source_padding)
-        if split_dim == "height":
+        self._padding = tuple(source_padding)
-            self.split_pad_left = int(self._source_padding[2])
+        self.register_buffer("_halo_recv_top_buf", None, persistent=False)
-            self.split_pad_right = int(self._source_padding[3])
+        self.register_buffer("_halo_recv_bottom_buf", None, persistent=False)
-            self.kernel_extent = self.kernel_size[-2]
+        self._trim_cache: dict[tuple[str, int], tuple[int, int, int]] = {}
-            self.stride_extent = self.stride[-2]
-            padding = (
-                self._source_padding[0],
-                self._source_padding[1],
-                0,
-                0,
-                self._source_padding[4],
-                self._source_padding[5],
-            )
-        else:
-            self.split_pad_left = int(self._source_padding[0])
-            self.split_pad_right = int(self._source_padding[1])
-            self.kernel_extent = self.kernel_size[-1]
-            self.stride_extent = self.stride[-1]
-            padding = (
-                0,
-                0,
-                self._source_padding[2],
-                self._source_padding[3],
-                self._source_padding[4],
-                self._source_padding[5],
-            )
-        self.halo_size = (self.kernel_extent - 1) // 2
-        self._padding = padding if self.halo_size > 0 else self._source_padding
-        self._halo_recv_top_buf: torch.Tensor | None = None
-        self._halo_recv_bottom_buf: torch.Tensor | None = None
-        self._trim_cache: dict[int, tuple[int, int, int]] = {}
 
-    def forward(self, x: torch.Tensor, cache_x: torch.Tensor | None = None) -> torch.Tensor:
+    def _spatial_shard_causal_conv_forward(
-        padding = list(self._padding)
+        self,
+        x: torch.Tensor,
+        cache_x: torch.Tensor | None = None,
+    ) -> torch.Tensor:
+        split_dim = _active_spatial_shard_split_dim()
+        padding = list(self._source_padding)
         if cache_x is not None and padding[4] > 0:
             cache_x = cache_x.to(x.device)
             x = torch.cat([cache_x, x], dim=2)
             padding[4] -= cache_x.shape[2]
 
+        if split_dim is None:
+            return nn.Conv3d.forward(self, F.pad(x, padding))
+
+        split_tensor_dim = _spatial_dim(split_dim)
+        if split_dim == "height":
+            split_pad_left = int(padding[2])
+            split_pad_right = int(padding[3])
+            kernel_extent = self.kernel_size[-2]
+            stride_extent = self.stride[-2]
+            padding[2] = 0
+            padding[3] = 0
+        else:
+            split_pad_left = int(padding[0])
+            split_pad_right = int(padding[1])
+            kernel_extent = self.kernel_size[-1]
+            stride_extent = self.stride[-1]
+            padding[0] = 0
+            padding[1] = 0
+        halo_size = (kernel_extent - 1) // 2
+
         x = F.pad(x, padding)
         x_padded, self._halo_recv_top_buf, self._halo_recv_bottom_buf = halo_exchange(
             x,
             group=self.group,
-            halo_size=self.halo_size,
+            halo_size=halo_size,
-            split_dim=self.split_dim,
+            split_dim=split_dim,
             recv_top_buf=self._halo_recv_top_buf,
             recv_bottom_buf=self._halo_recv_bottom_buf,
         )
-        shift, start, upper_bound = self._get_trim_params(x.shape[self.split_tensor_dim])
+        shift, start, upper_bound = self._get_trim_params(
+            x.shape[split_tensor_dim],
+            split_dim=split_dim,
+            halo_size=halo_size,
+            split_pad_left=split_pad_left,
+            split_pad_right=split_pad_right,
+            kernel_extent=kernel_extent,
+            stride_extent=stride_extent,
+        )
         if shift:
             x_padded = _narrow_along_dim(
                 x_padded,
-                self.split_tensor_dim,
+                split_tensor_dim,
                 shift,
-                x_padded.shape[self.split_tensor_dim] - shift,
+                x_padded.shape[split_tensor_dim] - shift,
             )
-        out = super().forward(x_padded)
+        out = nn.Conv3d.forward(self, x_padded)
-        out = _trim_local_conv_output(out, self.halo_size, start, upper_bound, split_dim=self.split_dim)
+        out = _trim_local_conv_output(out, halo_size, start, upper_bound, split_dim=split_dim)
-        return _zero_invalid_extent(out, split_dim=self.split_dim)
+        return _zero_invalid_extent(out, split_dim=split_dim)
 
-    def _get_trim_params(self, local_extent: int) -> tuple[int, int, int]:
+    def _get_trim_params(
-        trim_params = self._trim_cache.get(local_extent)
+        self,
+        local_extent: int,
+        *,
+        split_dim: str,
+        halo_size: int,
+        split_pad_left: int,
+        split_pad_right: int,
+        kernel_extent: int,
+        stride_extent: int,
+    ) -> tuple[int, int, int]:
+        cache_key = (split_dim, local_extent)
+        trim_params = self._trim_cache.get(cache_key)
         if trim_params is None:
             rank, world_size = _rank_world(self.group)
             trim_params = _compute_conv_trim_params(
                 local_extent=local_extent,
                 rank=rank,
                 world_size=world_size,
-                halo_size=self.halo_size,
+                halo_size=halo_size,
-                pad_before=self.split_pad_left,
+                pad_before=split_pad_left,
-                pad_after=self.split_pad_right,
+                pad_after=split_pad_right,
-                kernel_extent=self.kernel_extent,
+                kernel_extent=kernel_extent,
-                stride_extent=self.stride_extent,
+                stride_extent=stride_extent,
             )
-            self._trim_cache[local_extent] = trim_params
+            self._trim_cache[cache_key] = trim_params
         return trim_params
 
 
+class WanDistCausalConv3d(SpatialShardCausalConv3dMixin, nn.Conv3d):
+    # Cross-PR compatibility contract for the lossless Wan data-movement
+    # installer: it may fuse the no-context direct path, but must leave this
+    # wrapper in control whenever a spatial-shard context is active.
+    _vllm_omni_dynamic_spatial_shard_conv = True
+
+    def __init__(
+        self,
+        source: nn.Conv3d,
+        group: dist.ProcessGroup,
+    ):
+        super().__init__(
+            source.in_channels,
+            source.out_channels,
+            source.kernel_size,
+            stride=source.stride,
+            padding=0,
+            dilation=source.dilation,
+            groups=source.groups,
+            bias=source.bias is not None,
+            padding_mode=source.padding_mode,
+            device=source.weight.device,
+            dtype=source.weight.dtype,
+        )
+        self._init_spatial_shard_causal_conv(source, group)
+
+    def forward(self, x: torch.Tensor, cache_x: torch.Tensor | None = None) -> torch.Tensor:
+        return self._spatial_shard_causal_conv_forward(x, cache_x)
+
+
 def _compute_conv_trim_params(
     *,
     local_extent: int,
@@ -582,12 +673,15 @@ def _trim_local_conv_output(
     return out
 
 
-def _patch_attention_block(module: nn.Module, group: dist.ProcessGroup, split_dim: str) -> None:
+def _patch_attention_block(module: nn.Module, group: dist.ProcessGroup) -> None:
     if getattr(module, "_vllm_omni_spatial_shard_attention", False):
         return
     orig_forward = module.forward
 
     def _forward(self: nn.Module, x: torch.Tensor, *args: Any, **kwargs: Any) -> torch.Tensor:
+        split_dim = _active_spatial_shard_split_dim()
+        if split_dim is None:
+            return orig_forward(x, *args, **kwargs)
         _, world_size = _rank_world(group)
         if world_size <= 1:
             return orig_forward(x, *args, **kwargs)
@@ -609,60 +703,43 @@ def _replace_child(
     name: str,
     child: nn.Module,
     group: dist.ProcessGroup,
-    split_dim: str,
+    *,
+    causal_conv_class_name: str,
+    causal_conv_factory: Callable[[nn.Conv3d, dist.ProcessGroup], nn.Module],
 ) -> None:
-    if child.__class__.__name__ == "WanCausalConv3d":
+    if child.__class__.__name__ == causal_conv_class_name:
-        setattr(
+        setattr(parent, name, causal_conv_factory(child, group))
-            parent,
-            name,
-            WanDistCausalConv3d(
-                child,
-                group,
-                split_dim=split_dim,
-            ),
-        )
         return
     if isinstance(child, nn.ZeroPad2d):
         padding = tuple(int(p) for p in child.padding)
-        module_padding = padding
-        if parent.__class__.__name__ == "Sequential":
-            # Let the following WanDistConv2d account for global after-edge
-            # padding; this module handles the non-split dimension and before edge.
-            if split_dim == "height":
-                module_padding = (padding[0], padding[1], padding[2], 0)
-            else:
-                module_padding = (padding[0], 0, padding[2], padding[3])
         setattr(
             parent,
             name,
-            WanDistZeroPad2d(
+            SpatialShardZeroPad2d(
-                module_padding,
+                padding,
                 group,
-                split_dim=split_dim,
+                defer_split_after_padding=parent.__class__.__name__ == "Sequential",
-                split_padding=(padding[2], padding[3]) if split_dim == "height" else (padding[0], padding[1]),
             ),
         )
         return
     if isinstance(child, nn.Conv2d):
-        split_padding = None
+        deferred_padding = None
         if name == "1" and parent.__class__.__name__ == "Sequential":
-            # WanResample downsample uses ZeroPad2d((0, 1, 0, 1)) before a
+            # Wan/QwenImage downsampling uses ZeroPad2d((0, 1, 0, 1)) before a
             # stride-2 conv with padding=0.  Only the last rank should see the
             # bottom/right global padding, which is approximated by split_padding.
             prev = getattr(parent, "0", None)
-            if isinstance(prev, WanDistZeroPad2d):
+            if isinstance(prev, SpatialShardZeroPad2d):
-                split_padding = prev.split_padding
+                deferred_padding = prev.padding
             elif isinstance(prev, nn.ZeroPad2d):
-                pad = prev.padding
+                deferred_padding = tuple(int(value) for value in prev.padding)
-                split_padding = (int(pad[2]), int(pad[3])) if split_dim == "height" else (int(pad[0]), int(pad[1]))
         setattr(
             parent,
             name,
-            WanDistConv2d(
+            SpatialShardConv2d(
                 child,
                 group,
-                split_dim=split_dim,
+                deferred_padding=deferred_padding,
-                split_padding=split_padding,
             ),
         )
 
@@ -670,21 +747,45 @@ def _replace_child(
 def _patch_decoder_modules(
     module: nn.Module,
     group: dist.ProcessGroup,
-    split_dim: str,
+    *,
+    causal_conv_class_name: str,
+    causal_conv_factory: Callable[[nn.Conv3d, dist.ProcessGroup], nn.Module],
+    attention_block_class_name: str,
     inside_attention: bool = False,
 ) -> None:
-    if module.__class__.__name__ == "WanAttentionBlock":
+    if module.__class__.__name__ == attention_block_class_name:
-        _patch_attention_block(module, group, split_dim)
+        _patch_attention_block(module, group)
         inside_attention = True
 
     for name, child in list(module.named_children()):
-        if child.__class__.__name__ == "WanCausalConv3d":
+        if child.__class__.__name__ == causal_conv_class_name:
-            _replace_child(module, name, child, group, split_dim)
+            _replace_child(
+                module,
+                name,
+                child,
+                group,
+                causal_conv_class_name=causal_conv_class_name,
+                causal_conv_factory=causal_conv_factory,
+            )
             continue
         if isinstance(child, nn.Conv2d) and not inside_attention:
-            _replace_child(module, name, child, group, split_dim)
+            _replace_child(
+                module,
+                name,
+                child,
+                group,
+                causal_conv_class_name=causal_conv_class_name,
+                causal_conv_factory=causal_conv_factory,
+            )
             continue
-        _patch_decoder_modules(child, group, split_dim, inside_attention=inside_attention)
+        _patch_decoder_modules(
+            child,
+            group,
+            causal_conv_class_name=causal_conv_class_name,
+            causal_conv_factory=causal_conv_factory,
+            attention_block_class_name=attention_block_class_name,
+            inside_attention=inside_attention,
+        )
 
 
 def _decoder_upsample_count(decoder: nn.Module) -> int:
@@ -695,47 +796,58 @@ def _decoder_upsample_count(decoder: nn.Module) -> int:
     return count
 
 
-def install_wan_spatial_shard_decode(vae: Any, group: dist.ProcessGroup, split_dim: str = "height") -> None:
+def clear_spatial_shard_runtime_buffers(vae: SpatialShardVAE) -> None:
+    decoder = getattr(vae, "decoder", None)
+    if decoder is None:
+        return
+    for module in decoder.modules():
+        if "_halo_recv_top_buf" in module._buffers:
+            module._halo_recv_top_buf = None
+        if "_halo_recv_bottom_buf" in module._buffers:
+            module._halo_recv_bottom_buf = None
+
+
+def install_spatial_shard_decode(
+    vae: SpatialShardVAE,
+    group: dist.ProcessGroup,
+    split_dim: str,
+    *,
+    causal_conv_class_name: str,
+    causal_conv_factory: Callable[[nn.Conv3d, dist.ProcessGroup], nn.Module],
+    attention_block_class_name: str,
+    installed_attr: str,
+    model_name: str,
+) -> None:
     """Patch ``vae.decoder`` once for spatially-sharded decode.
 
     This mutates the already-loaded decoder in place by swapping its spatial
-    convolutions/padding for halo-exchanging variants and wrapping
+    convolutions/padding for context-aware variants and attaching a dedicated
-    ``decoder.forward``. The patch is permanent for the lifetime of the VAE
+    spatial forward. Outside that forward the replacements execute their exact
-    instance and is applied only once (subsequent calls are no-ops). A given
+    local PyTorch behavior, so a later auto-selected tile request remains safe.
-    instance is bound to a single ``split_dim``; switching between
+    The same installed decoder can alternate height and width sharding.
-    ``"height"`` and ``"width"`` requires a fresh VAE instance and raises here
-    otherwise.
 
-    Only group-relative rank 0 assembles the final decoded frame, mirroring the
+    Group-relative rank 0 assembles the final decoded frame. The model adapter
-    distributed tiled-decode ``broadcast_result=False`` contract; the other ranks
+    then preserves its prior contract: Wan keeps the result on rank 0, while
-    take part in the collectives but return an empty placeholder.
+    QwenImage broadcasts it to every rank.
     """
     _spatial_dim(split_dim)
-    if getattr(vae, "_vllm_omni_wan_spatial_shard_installed", False):
+    if getattr(vae, installed_attr, False):
-        installed_split_dim = getattr(vae, "_vllm_omni_wan_spatial_shard_split_dim", "height")
-        if installed_split_dim != split_dim:
-            raise ValueError(
-                "Wan spatial-shard VAE decoder was already patched for "
-                f"{installed_split_dim!r} split; create a fresh VAE instance to use {split_dim!r} split."
-            )
         return
     decoder = getattr(vae, "decoder", None)
     if decoder is None:
-        raise ValueError("Wan spatial-shard VAE decode requires a decoder module.")
+        raise ValueError(f"{model_name} spatial-shard VAE decode requires a decoder module.")
 
-    _patch_decoder_modules(decoder, group, split_dim)
+    _patch_decoder_modules(
+        decoder,
+        group,
+        causal_conv_class_name=causal_conv_class_name,
+        causal_conv_factory=causal_conv_factory,
+        attention_block_class_name=attention_block_class_name,
+    )
     upsample_count = _decoder_upsample_count(decoder)
     orig_forward = decoder.forward
 
-    def _forward(
+    def _forward(self: nn.Module, x: torch.Tensor, *args: object, split_dim: str, **kwargs: object) -> torch.Tensor:
-        self: nn.Module,
-        x: torch.Tensor,
-        feat_cache: list[torch.Tensor] | None = None,
-        feat_idx: list[int] | None = None,
-        first_chunk: bool = False,
-    ) -> torch.Tensor:
-        if feat_idx is None:
-            feat_idx = [0]
         tensor_dim = _spatial_dim(split_dim)
         input_extent = x.shape[tensor_dim]
         x, expected_extent = split_for_parallel_decode(
@@ -755,29 +867,50 @@ def install_wan_spatial_shard_decode(vae: Any, group: dist.ProcessGroup, split_d
             )
         )
         try:
-            out = orig_forward(x, feat_cache=feat_cache, feat_idx=feat_idx, first_chunk=first_chunk)
+            out = orig_forward(x, *args, **kwargs)
         finally:
             _SPATIAL_SHARD_CONTEXT.reset(token)
         return gather_and_trim_extent(out, expected_extent=expected_extent, split_dim=split_dim, group=group, dst=0)
 
-    decoder.forward = MethodType(_forward, decoder)
+    decoder._vllm_omni_spatial_shard_forward = MethodType(_forward, decoder)
-    vae._vllm_omni_wan_spatial_shard_installed = True
+    setattr(vae, installed_attr, True)
-    vae._vllm_omni_wan_spatial_shard_split_dim = split_dim
+    logger.info("Installed %s VAE dynamic-axis spatial-shard decode.", model_name)
-    logger.info("Installed Wan VAE %s-sharded decode.", split_dim)
 
 
-def spatial_shard_decode(
+def install_wan_spatial_shard_decode(
-    vae: Any,
+    vae: SpatialShardVAE,
+    group: dist.ProcessGroup,
+    split_dim: str = "height",
+) -> None:
+    install_spatial_shard_decode(
+        vae,
+        group,
+        split_dim,
+        causal_conv_class_name="WanCausalConv3d",
+        causal_conv_factory=WanDistCausalConv3d,
+        attention_block_class_name="WanAttentionBlock",
+        installed_attr="_vllm_omni_wan_spatial_shard_installed",
+        model_name="Wan",
+    )
+
+
+def spatial_shard_decode_impl(
+    vae: SpatialShardVAE,
     z: torch.Tensor,
     *,
     group: dist.ProcessGroup,
+    install: Callable[[SpatialShardVAE, dist.ProcessGroup, str], None],
+    model_name: str,
+    pass_first_chunk: bool,
+    broadcast_result: bool,
+    unpatchify_patch_size: int | None,
     return_dict: bool = True,
     split_dim: str = "height",
 ) -> DecoderOutput | tuple[torch.Tensor]:
-    install_wan_spatial_shard_decode(vae, group, split_dim=split_dim)
+    install(vae, group, split_dim)
 
     if z.shape[2] == 0:
-        raise ValueError("Wan spatial-shard VAE decode expects at least one latent frame.")
+        raise ValueError(f"{model_name} spatial-shard VAE decode expects at least one latent frame.")
 
     # Non-rank-0 ranks must still run the decoder every chunk to stay in lockstep with
     # the halo/all-gather collectives; they just skip keeping/assembling the output.
@@ -786,31 +919,72 @@ def spatial_shard_decode(
 
     vae.clear_cache()
     try:
-        context = vae._execution_context() if hasattr(vae, "_execution_context") else nullcontext()
+        context_factory = getattr(vae, "_execution_context", None)
+        context = context_factory() if callable(context_factory) else nullcontext()
         with context:
             x = vae.post_quant_conv(z)
             decoded_chunks = []
+            spatial_forward = getattr(vae.decoder, "_vllm_omni_spatial_shard_forward")
             for i in range(z.shape[2]):
                 vae._conv_idx = [0]
-                chunk = vae.decoder(
+                if pass_first_chunk:
+                    chunk = spatial_forward(
                         x[:, :, i : i + 1, :, :],
                         feat_cache=vae._feat_map,
                         feat_idx=vae._conv_idx,
-                    first_chunk=(i == 0),
+                        first_chunk=i == 0,
+                        split_dim=split_dim,
+                    )
+                else:
+                    chunk = spatial_forward(
+                        x[:, :, i : i + 1, :, :],
+                        feat_cache=vae._feat_map,
+                        feat_idx=vae._conv_idx,
+                        split_dim=split_dim,
                     )
                 if produce_output:
                     decoded_chunks.append(chunk)
 
             if produce_output:
                 out = torch.cat(decoded_chunks, dim=2)
-                if vae.config.patch_size is not None:
+                if unpatchify_patch_size is not None:
-                    out = unpatchify(out, patch_size=vae.config.patch_size)
+                    out = unpatchify(out, patch_size=unpatchify_patch_size)
                 out = torch.clamp(out, min=-1.0, max=1.0)
             else:
                 out = z.new_zeros(0)
     finally:
         vae.clear_cache()
+        # Halo buffers are request-shape scratch space allocated outside the
+        # tagged weight pool. Drop live references so sleep/offload never has
+        # to preserve or discard them as model state.
+        clear_spatial_shard_runtime_buffers(vae)
+
+    if broadcast_result:
+        out = vae.distributed_executor._sync_final_result(out, z.ndim, z.device, vae.dtype)
 
     if not return_dict:
         return (out,)
     return DecoderOutput(sample=out)
+
+
+def spatial_shard_decode(
+    vae: SpatialShardVAE,
+    z: torch.Tensor,
+    *,
+    group: dist.ProcessGroup,
+    return_dict: bool = True,
+    split_dim: str = "height",
+) -> DecoderOutput | tuple[torch.Tensor]:
+    """Decode a Wan latent with spatial activation sharding."""
+    return spatial_shard_decode_impl(
+        vae,
+        z,
+        group=group,
+        install=install_wan_spatial_shard_decode,
+        model_name="Wan",
+        pass_first_chunk=True,
+        broadcast_result=False,
+        unpatchify_patch_size=vae.config.patch_size,
+        return_dict=return_dict,
+        split_dim=split_dim,
+    )

vllm_omni/diffusion/layers/norm.py

@@ -68,6 +68,7 @@ class RMSNorm(CustomOp):
     def __init__(self, hidden_size: int, eps: float = 1e-6, dtype: torch.dtype = torch.float32) -> None:
         super().__init__()
         self.weight = nn.Parameter(torch.ones(hidden_size, dtype=dtype))
+        self.hidden_size = hidden_size
         self.variance_epsilon = eps
 
     def _forward_fused(self, x: torch.Tensor) -> torch.Tensor:
@@ -107,6 +108,19 @@ class RMSNorm(CustomOp):
         except Exception:
             return self.forward_native(x)
 
+    def forward_musa(
+        self,
+        x: torch.Tensor,
+    ) -> torch.Tensor:
+        # Preserve the aten::rms_norm graph so dynamic Inductor can fuse the
+        # H3 Q/K norm with its inline RoPE path on MUSA.
+        return F.rms_norm(
+            x,
+            (self.hidden_size,),
+            self.weight,
+            self.variance_epsilon,
+        )
+
     def forward_npu(
         self,
         x: torch.Tensor,

vllm_omni/diffusion/layers/rope.py

@@ -193,7 +193,16 @@ class RotaryEmbedding(CustomOp):
         cos: torch.Tensor,
         sin: torch.Tensor,
     ) -> torch.Tensor:
+        # Keep the full-dimension NeoX form inline for MUSA compilation.
+        # Other layouts use the shared native implementation.
+        if self.half_head_dim or self.interleaved:
             return self.forward_native(x, cos, sin)
+        if cos.dim() == 3:
+            cos, sin = cos[0], sin[0]
+        cos = cos.unsqueeze(-2)
+        sin = sin.unsqueeze(-2)
+        x1, x2 = x.chunk(2, dim=-1)
+        return x * cos + torch.cat((-x2, x1), dim=-1) * sin
 
     def forward_native(
         self,

vllm_omni/diffusion/models/minimax_h3/minimax_h3_transformer.py

@@ -107,6 +107,15 @@ MINIMAX_H3_FP32_BUFFER_NAMES = frozenset({"rope.inv_freq"})
 # lookup and masked out afterwards).
 MINIMAX_H3_ADALN_MODALITY_NUM = 3
 
+# Opt-in fp16-range protection for the NPU ascend_laser_attention kernel
+# (consumed only via the "laser_input_scale" extra key; other backends and
+# platforms ignore it). The kernel stores unscaled QK^T in an fp16 GM
+# workspace, and H3's outlier activations (per-element amax in the hundreds)
+# push dot products past fp16 max 65504, turning whole 128-row blocks NaN.
+# 256 is a power of two, so pre-dividing q/k/v and the compensating
+# kernel-scale/output multiplies are exact in floating point.
+MINIMAX_H3_LASER_INPUT_SCALE = 256.0
+
 
 def _required_kwarg(kwargs: dict[str, Any], key: str) -> Any:
     if key not in kwargs or kwargs[key] is None:
@@ -333,6 +342,7 @@ class MiniMaxH3Attention(nn.Module):
         )
         self.num_heads = self.qkv_proj.num_heads
         self.num_kv_heads = self.qkv_proj.num_kv_heads
+        self.rot_dim = 6 * arch.rope_inv_freq_len
         self.q_norm = _norm(arch.attention_head_dim, eps=arch.qk_norm_eps)
         self.k_norm = _norm(arch.attention_head_dim, eps=arch.qk_norm_eps)
         self.rope = RotaryEmbedding(is_neox_style=True, half_head_dim=False)
@@ -365,7 +375,7 @@ class MiniMaxH3Attention(nn.Module):
         x: [T, heads, head_dim]; freqs: [T, rot_dim]. In the unfused path, cos/sin
         are cast to the activation dtype before the elementwise math.
         """
-        rot_dim = freqs.shape[-1]
+        rot_dim = self.rot_dim
         x_rot, x_pass = x[..., :rot_dim], x[..., rot_dim:]
         cos = torch.cos(freqs).to(x.dtype)  # [T, rot_dim]
         sin = torch.sin(freqs).to(x.dtype)
@@ -401,11 +411,16 @@ class MiniMaxH3Attention(nn.Module):
         used = min(max_seqlen, packed_total)
         attn_mask = None
         # Ring attention can dispatch to a different implementation from the
-        # configured backend, so this no-mask fast path is local-only.
+        # configured backend, so the no-mask fast paths are local-only.
-        prefix_slice = (
+        # supports_prefix_kv_slicing: backend slices K/V itself (cuDNN).
-            not getattr(self.attention, "use_ring", False) and self.attention.attn_backend.supports_prefix_kv_slicing
+        # supports_packed_mask_free: backend consumes the packed metadata
+        # without ever reading attn_mask (CUDA packed varlen, NPU
+        # npu_attn_varlen opt-in with its own fallback rebuild).
+        no_mask = not getattr(self.attention, "use_ring", False) and (
+            self.attention.attn_backend.supports_prefix_kv_slicing
+            or self.attention.attn_backend.supports_packed_mask_free()
         )
-        if used < packed_total and not prefix_slice:
+        if used < packed_total and not no_mask:
             attn_mask = torch.arange(packed_total, device=q.device)[None] < used
         metadata = AttentionMetadata(
             attn_mask=attn_mask,
@@ -415,6 +430,15 @@ class MiniMaxH3Attention(nn.Module):
                 "max_seqlen_q": max_seqlen,
                 "max_seqlen_k": max_seqlen,
                 "valid_kv_length": used,
+                # Opt the NPU flash backend into the packed varlen path so the
+                # quadratic full_qk mask is never materialized. Ring attention
+                # is excluded: it keeps the aligned padding rows for its
+                # fixed-size P2P buffers and still needs the mask.
+                "npu_attn_varlen": not getattr(self.attention, "use_ring", False),
+                # fp16-range protection for the ascend_laser_attention kernel
+                # (see MINIMAX_H3_LASER_INPUT_SCALE). Ignored by every other
+                # backend/path.
+                "laser_input_scale": MINIMAX_H3_LASER_INPUT_SCALE,
             },
             video_layout=video_layout,
         )

vllm_omni/diffusion/models/minimax_h3/vae.py

@@ -155,6 +155,11 @@ class MiniMaxH3VideoVAE(nn.Module, DistributedVaeMixin):
         parallel_size: int,
         mode: str = "tile",
     ) -> None:
+        # ``auto`` is the cross-model default. MiniMax H3 has no spatial-shard
+        # capability, so preserve its native tile path for that default while
+        # continuing to reject explicitly requested spatial modes.
+        if mode == "auto":
+            mode = "tile"
         if mode != "tile":
             raise ValueError(f"MiniMax H3 VAE supports its native tile parallel mode only, got {mode!r}")
         group = get_dit_group()

vllm_omni/diffusion/worker/diffusion_model_runner.py

@@ -30,6 +30,9 @@ from vllm_omni.diffusion.cache.prompt_embed_cache import (
 from vllm_omni.diffusion.cache.selector import get_cache_backend
 from vllm_omni.diffusion.compile import regionally_compile
 from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
+from vllm_omni.diffusion.distributed.autoencoders.spatial_shard import (
+    prepare_pipeline_spatial_shard_decode,
+)
 from vllm_omni.diffusion.forward_context import set_forward_context
 from vllm_omni.diffusion.model_loader.diffusers_loader import DiffusersPipelineLoader
 from vllm_omni.diffusion.models.interface import (
@@ -243,6 +246,7 @@ class DiffusionModelRunner(OmniConnectorModelRunnerMixin):
                     custom_pipeline_name=custom_pipeline_name,
                     device=self.device,
                 )
+                prepare_pipeline_spatial_shard_decode(self.pipeline)
         time_after_load = time.perf_counter()
 
         logger.info(

vllm_omni/engine/arg_utils.py

@@ -505,7 +505,7 @@ class OrchestratorArgs:
     diffusion_kv_cache_skip_layers: str | None = None
     cfg_parallel_size: int = 1
     vae_patch_parallel_size: int = 1
-    vae_parallel_mode: str = "tile"
+    vae_parallel_mode: str = "auto"
     text_encoder_tp_size: int = 1
     default_sampling_params: str | None = None
     max_generated_image_size: int | None = None

vllm_omni/engine/async_omni_engine.py

@@ -972,7 +972,7 @@ class AsyncOmniEngine:
             cfg_parallel_size = normalized_kwargs.get("cfg_parallel_size") or 1
             pipeline_parallel_size = normalized_kwargs.get("pipeline_parallel_size") or 1
             vae_patch_parallel_size = normalized_kwargs.get("vae_patch_parallel_size") or 1
-            vae_parallel_mode = normalized_kwargs.get("vae_parallel_mode") or "tile"
+            vae_parallel_mode = normalized_kwargs.get("vae_parallel_mode") or "auto"
             text_encoder_tp_size = normalized_kwargs.get("text_encoder_tp_size") or 1
             enable_expert_parallel = normalized_kwargs.get("enable_expert_parallel") or False
             use_hsdp = normalized_kwargs.get("use_hsdp", False)

vllm_omni/entrypoints/cli/serve.py

@@ -750,10 +750,12 @@ class OmniServeCommand(CLISubcommand):
         omni_config_group.add_argument(
             "--vae-parallel-mode",
             type=str,
-            default="tile",
+            default="auto",
-            choices=["tile", "spatial_shard_height", "spatial_shard_width"],
+            choices=["auto", "tile", "spatial_shard_height", "spatial_shard_width"],
             help="VAE parallel decode strategy for diffusion models. "
-            "'tile' (default) uses patch/tile parallel decode; "
+            "'auto' (default) selects the longer spatial-shard axis for validated Wan and distributed QwenImage "
+            "tiled decodes "
+            "on a full DiT group, then falls back to patch/tile decode; 'tile' always uses patch/tile decode; "
             "'spatial_shard_height'/'spatial_shard_width' use spatially-sharded decode that splits "
             "decoder feature maps along height/width and exchanges halo regions. The "
             "'spatial_shard_*' modes require vae_patch_parallel_size to match the DiT group size. "

vllm_omni/platforms/npu/platform.py

@@ -139,6 +139,18 @@ class NPUOmniPlatform(OmniPlatform, NPUPlatform):
                 )
                 backend_upper = "FLASH_ATTN"
 
+            if backend_upper == "FLASH_ATTN" and find_spec("mindiesd"):
+                # The NPU FLASH_ATTN backend imports mindiesd lazily at first
+                # forward, but CANN snapshots the custom-op registry at the
+                # first custom-op regInfo lookup in the process (e.g. a
+                # vllm-ascend custom op during model load/warmup). Import
+                # mindiesd here so its env.py prepends the mindiesd vendor
+                # dirs (aie_ascendc etc.) to ASCEND_CUSTOM_OPP_PATH before
+                # that snapshot; otherwise aclnnLaserAttention /
+                # FusedAttentionScore fail with EZ1001 "does not support
+                # opType" for the rest of the process.
+                import mindiesd  # noqa: F401
+
             backend = DiffusionAttentionBackendEnum[backend_upper]
             logger.debug("Using diffusion attention backend '%s'", backend_upper)
             return backend.get_path()