Zhang JianandChendi Xue b1809985ef [recipe] Add cosmos3-nano recipe for npu (1xA3) (#4978) ...

Signed-off-by: Zhang Jian <jianmusings@gmail.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Chendi Xue <chendi.xue@intel.com>

2026-07-14 16:19:44 +08:00

..

attention

[Diffusion] Improve HuggingFace hub kernel loading in flash_attn_hub (#4977)

2026-07-09 12:10:10 +08:00

cache

[Model] Add Krea 2 text-to-image diffusion model (#4730)

2026-07-11 16:25:41 -07:00

distributed

[Bugfix] Fix HunyuanImage3 MoE groups for vLLM 0.24 (#4893)

2026-07-05 15:37:42 +00:00

executor

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

hooks

[Feat] Support MagCache (#1287)

2026-05-29 22:26:23 +08:00

layers

[BugFix] fix possible shape mismatch when using ROPE (#4655)

2026-07-07 17:54:39 +08:00

lora

[Feature] Improve diffusion LoRA compatibility for SDXL (#4825)

2026-07-01 23:41:16 +00:00

model_loader

Extend Cosmos3 CPU offloading to component and layerwise paths (#4695)

2026-07-13 09:48:53 +00:00

models

[recipe] Add cosmos3-nano recipe for npu (1xA3) (#4978)

2026-07-14 16:19:44 +08:00

offloader

Extend Cosmos3 CPU offloading to component and layerwise paths (#4695)

2026-07-13 09:48:53 +00:00

postprocess

[Bugfix] Fix RIFE device selection for CPU-transported videos (#2876)

2026-04-17 19:19:34 +08:00

profiler

[Bugfix] Report stepwise Qwen-Image profiler metrics (#4517)

2026-07-03 04:32:22 +00:00

quantization

[Rebase] Rebase to vllm v0.24.0 (#4709)

2026-06-30 19:41:06 +08:00

sched

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

utils

[feat] Streaming diffusion video generation output (#3737)

2026-06-23 09:57:53 +00:00

worker

[BDE] Phase 1: engine-level KV cache management for DreamZero (RFC #4366) (#4534)

2026-07-05 07:17:58 +08:00

__init__.py

[Diffusion] Qwen image support (#82)

2025-11-28 14:22:11 +08:00

compile.py

[Bugfix][CI]Fix HSDP regional compile boundary (#4668)

2026-06-25 02:52:52 +00:00

config.py

[Diffusion][Attention] Support per-role attention backend via CLI (#2681)

2026-05-10 11:59:05 +08:00

data.py

[Bugfix][sleep mode]: guard generation on partial wake and ensure wake idempotency (#4834)

2026-07-05 14:50:08 +00:00

diffusion_engine.py

[BDE] Phase 1: engine-level KV cache management for DreamZero (RFC #4366) (#4534)

2026-07-05 07:17:58 +08:00

envs.py

[Refactor] Extract has_flash_attn_pkg in OmniPlatform (#3068)

2026-04-27 04:07:34 +00:00

forward_context.py

Wan2.2: Fix the bug of using cache-dit with ulysses in t2v and i2v (#3927)

2026-06-25 15:15:59 +00:00

inline_stage_diffusion_client.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

io_support.py

[Refactor]Base class for dit pipelines with unified parameter declaration[1/N] (#4225)

2026-06-18 17:14:18 +08:00

ipc.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

model_metadata.py

[Feature] HunyuanImage-3.0 IT2I: multi-image input + prompt API cleanup (#3444)

2026-05-14 16:58:40 +08:00

output_formatter.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

registry.py

[Model] Add Krea 2 text-to-image diffusion model (#4730)

2026-07-11 16:25:41 -07:00

request.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

stage_diffusion_client.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00

stage_diffusion_proc.py

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

2026-06-29 18:09:19 +02:00