Merge origin/main to resolve TTS ratchet conflict

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

docs/.nav.yml

@@ -16,21 +16,31 @@ 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
-      - Speech-To-Video: user_guide/examples/offline_inference/speech_to_video.md
+      - InternVLA-A1: user_guide/examples/offline_inference/internvla_a1.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
-      - Speech-To-Video: user_guide/examples/online_serving/speech_to_video.md
+      - MiMo-Audio: user_guide/examples/online_serving/mimo_audio.md
-      - Text-To-Image: user_guide/examples/online_serving/text_to_image.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-Video: user_guide/examples/online_serving/text_to_video.md
   - General:
     - usage/*

docs/mkdocs/hooks/generate_examples.py

@@ -24,22 +24,15 @@ SERVING_MODE_TITLES = {
     "online_serving": "Online serving",
 }
 
-# Keep the Examples navigation focused on reusable modality/task entry points.
+# Generated example pages keep their source-derived URLs even when their
-# Model-specific scripts remain available under ``examples/`` and are surfaced
+# navigation category changes. Quantization helpers are feature documentation,
-# from these shared pages instead of getting one page per model.
+# not user-serving examples, so keep them under the existing Features /
-GENERAL_EXAMPLE_SLUGS = frozenset(
+# Quantization section instead of creating a second top-level Quantization
-    {
+# category under Examples.
-        "image_to_image",
+EXAMPLE_NAV_TARGETS = {
-        "image_to_video",
+    "quantization": "quantization",
-        "speech_to_video",
-        "text_to_audio",
-        "text_to_image",
-        "text_to_speech",
-        "text_to_video",
-        "x_to_text",
-        "x_to_video_audio",
 }
-)
+GENERATED_QUANTIZATION_EXAMPLES_TITLE = "Generated Examples"
 
 
 def load_model_display_names() -> dict[str, str]:
@@ -63,13 +56,6 @@ 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",
@@ -372,9 +358,12 @@ def update_nav_file(examples: list[Example]):
             items.append({example.nav_title: rel_path.as_posix()})
         return items
 
-    # Build the new Examples section - start with preserved items.
+    # Build the new Examples section - start with preserved items. Categories
+    # not explicitly routed elsewhere retain the historical Examples behavior.
     examples_section = preserved_items.copy()
     for category in sorted(examples_by_category.keys()):
+        if EXAMPLE_NAV_TARGETS.get(category, "examples") != "examples":
+            continue
         items = category_items(category)
         if items:
             category_title = fix_case(category.replace("_", " ").title())
@@ -383,6 +372,36 @@ def update_nav_file(examples: list[Example]):
     # Update the nav structure
     nav_list[user_guide_idx]["User Guide"][examples_idx]["Examples"] = examples_section
 
+    features_content = next(
+        (item["Features"] for item in user_guide_content if isinstance(item, dict) and "Features" in item),
+        None,
+    )
+    quantization_content = None
+    if isinstance(features_content, list):
+        quantization_content = next(
+            (item["Quantization"] for item in features_content if isinstance(item, dict) and "Quantization" in item),
+            None,
+        )
+
+    if isinstance(quantization_content, list):
+        # Remove only the group owned by this hook so repeated builds are
+        # idempotent and hand-authored Quantization navigation is retained.
+        quantization_content[:] = [
+            item
+            for item in quantization_content
+            if not (isinstance(item, dict) and GENERATED_QUANTIZATION_EXAMPLES_TITLE in item)
+        ]
+
+    quantization_examples = examples_by_category.get("quantization")
+    if quantization_examples:
+        if not isinstance(quantization_content, list):
+            logger.warning(
+                "Could not find 'User Guide' -> 'Features' -> 'Quantization' section; "
+                "omitting generated quantization examples from navigation"
+            )
+        else:
+            quantization_content.append({GENERATED_QUANTIZATION_EXAMPLES_TITLE: category_items("quantization")})
+
     # Write back to file
     nav_data["nav"] = nav_list
     with open(NAV_FILE, "w", encoding="utf-8") as f:
@@ -413,8 +432,6 @@ 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"

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

@@ -4,17 +4,6 @@ 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) |
@@ -22,8 +11,7 @@ Validated on:
 | Unified memory | 128 GB LPDDR5X (~121 GiB usable) |
 | GPUs | 1 |
 | Checkpoint storage | 135 GiB per partition |
-| Measured peak allocator high-water, T2VA (FP8) | 97.7 GiB |
+| Measured peak allocator high-water (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.
@@ -41,21 +29,9 @@ 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, T2VA leaves roughly
+With ~97.7 GiB of the pool held by the allocator at peak, there is roughly 23 GiB
-23 GiB of headroom for the OS, page cache, and any other process on the box.
+of headroom for the OS, page cache, and any other process on the box. Treat this
-Ref2VA is tighter on both counts. The allocator high-water rises to 102.8 GiB,
+platform as single-tenant while a request is in flight.
-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
 
@@ -118,52 +94,6 @@ 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:
@@ -172,69 +102,32 @@ 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`. The keys are
+  `X-Stage-Durations` response header of `/v1/videos/sync`.
-  `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]`. See the
+  memory has no discrete VRAM to report and the field returns `[N/A]`.
-  capacity section for a `/proc/meminfo` cross-check.
+- Text encode and VAE decode were measured on a separate 10-step run at the same
-- For T2VA, text encode and VAE decode were measured on a separate 10-step run at
+  960x576 / 8 s geometry. Both are independent of step count, so they transfer to
-  the same 960x576 / 8 s geometry. Both are independent of step count, so they
+  the 50-step row unchanged.
-  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.
 
-Ref2VA costs 1.92x the wall clock of T2VA at the same geometry and step count:
+Repeated identical 10-step requests varied by up to 23% in denoise time
-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, and 7200 s is
+default 1800 s is shorter than a 50-step run on this platform.
-shorter than a 50-step Ref2VA run.
 
 ## Known limitations
 
@@ -246,17 +139,11 @@ shorter than a 50-step Ref2VA run.
 - `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 notes above.
+- Sustained load degrades throughput. See the variance note above.
 - Only one partition is resident. For Ref2VA, stop the FL2VA server and restart
-  with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA with one reference image is measured
+  the same command with `/path/to/MiniMax-H3/Ref2VA`. Ref2VA reference video
-  above; reference videos and additional images push the token count higher and
+  count and prompt length increase activation memory; begin with one request at
-  were not measured. With `MemAvailable` bottoming out at 7.4 GiB during a
+  a time and keep the short edge at 576.
-  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.
-```

tests/diffusion/models/minimax_h3/test_minimax_h3_parallel.py

@@ -69,7 +69,6 @@ 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
 

tests/docs/test_generate_examples.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from types import SimpleNamespace
 
 import pytest
+import yaml
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
@@ -46,9 +47,111 @@ def test_model_display_names_require_string_mapping(tmp_path, monkeypatch):
         generate_examples.load_model_display_names()
 
 
-def test_only_general_serving_examples_get_generated_pages():
+def test_quantization_examples_keep_source_urls_under_feature_navigation(tmp_path, monkeypatch):
-    general_example = SimpleNamespace(category="offline_inference", path=Path("text_to_image"))
+    nav_file = tmp_path / "docs" / ".nav.yml"
-    model_example = SimpleNamespace(category="offline_inference", path=Path("qwen3_omni"))
+    nav_file.parent.mkdir(parents=True)
+    nav_file.write_text(
+        yaml.safe_dump(
+            {
+                "nav": [
+                    {
+                        "User Guide": [
+                            {
+                                "Examples": [
+                                    "examples/README.md",
+                                    {"Offline Inference": [{"Old": "user_guide/examples/offline_inference/old.md"}]},
+                                ]
+                            },
+                            {"Features": [{"Quantization": [{"Overview": "user_guide/quantization/overview.md"}]}]},
+                        ]
+                    }
+                ]
+            },
+            sort_keys=False,
+        ),
+        encoding="utf-8",
+    )
 
-    assert generate_examples.is_general_example(general_example)
+    monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
-    assert not generate_examples.is_general_example(model_example)
+    monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
+    monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
+
+    quantization_example = SimpleNamespace(
+        category="quantization",
+        path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
+        nav_title="Check Modelopt FP8 Export",
+    )
+    offline_example = SimpleNamespace(
+        category="offline_inference",
+        path=tmp_path / "examples/offline_inference/demo.py",
+        nav_title="Demo",
+    )
+
+    generate_examples.update_nav_file([quantization_example, offline_example])
+    generate_examples.update_nav_file([quantization_example, offline_example])
+
+    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
+    user_guide = nav_data["nav"][0]["User Guide"]
+    examples = next(item["Examples"] for item in user_guide if "Examples" in item)
+    features = next(item["Features"] for item in user_guide if "Features" in item)
+    quantization = next(item["Quantization"] for item in features if "Quantization" in item)
+
+    assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
+    generated_examples = [
+        item[generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE]
+        for item in quantization
+        if generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
+    ]
+    assert len(generated_examples) == 1
+    assert generated_examples[0] == [
+        {"Check Modelopt FP8 Export": "user_guide/examples/quantization/check_modelopt_fp8_export.md"}
+    ]
+
+    # A later build without quantization examples must not leave a stale
+    # generated group in the hand-authored Quantization section.
+    generate_examples.update_nav_file([offline_example])
+    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
+    user_guide = nav_data["nav"][0]["User Guide"]
+    features = next(item["Features"] for item in user_guide if "Features" in item)
+    quantization = next(item["Quantization"] for item in features if "Quantization" in item)
+    assert not any(
+        isinstance(item, dict) and generate_examples.GENERATED_QUANTIZATION_EXAMPLES_TITLE in item
+        for item in quantization
+    )
+
+
+def test_quantization_examples_are_not_added_to_examples_without_feature_target(tmp_path, monkeypatch, caplog):
+    nav_file = tmp_path / "docs" / ".nav.yml"
+    nav_file.parent.mkdir(parents=True)
+    nav_file.write_text(
+        yaml.safe_dump(
+            {
+                "nav": [
+                    {
+                        "User Guide": [
+                            {"Examples": ["examples/README.md"]},
+                        ]
+                    }
+                ]
+            },
+            sort_keys=False,
+        ),
+        encoding="utf-8",
+    )
+
+    monkeypatch.setattr(generate_examples, "ROOT_DIR", tmp_path)
+    monkeypatch.setattr(generate_examples, "NAV_FILE", nav_file)
+    monkeypatch.setattr(generate_examples, "EXAMPLE_DOC_DIR", tmp_path / "docs/user_guide/examples")
+
+    quantization_example = SimpleNamespace(
+        category="quantization",
+        path=tmp_path / "examples/quantization/check_modelopt_fp8_export.py",
+        nav_title="Check Modelopt FP8 Export",
+    )
+
+    generate_examples.update_nav_file([quantization_example])
+
+    nav_data = yaml.safe_load(nav_file.read_text(encoding="utf-8"))
+    examples = nav_data["nav"][0]["User Guide"][0]["Examples"]
+    assert not any(isinstance(item, dict) and "Quantization" in item for item in examples)
+    assert "omitting generated quantization examples from navigation" in caplog.text

vllm_omni/diffusion/layers/norm.py

@@ -68,7 +68,6 @@ 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:
@@ -108,19 +107,6 @@ 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

@@ -193,16 +193,7 @@ 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

@@ -333,7 +333,6 @@ 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)
@@ -366,7 +365,7 @@ 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 = self.rot_dim
+        rot_dim = freqs.shape[-1]
         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)