vllm-omni

attention

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535 )

2026-09-16 15:47:31 +08:00

cache

[Attention] [P1] Keep H3 VSA policy in the model and share sparse primitives (#7535 )

2026-09-16 15:47:31 +08:00

diffusion_kv

[Rebase] Rebase to vLLM 0.29.0 (#7230 )

2026-09-10 12:08:28 +08:00

distributed

[2/N] Add a minimal temporal chunk callback for MiniMax-H3 (#7017 )

2026-09-09 16:40:32 +08:00

executor

[Bugfix] Escalate diffusion worker shutdown and retain survivors (#7126 )

2026-09-10 17:56:44 +08:00

hooks

[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (#5717 )

2026-09-06 16:23:30 +08:00

interaction

[Core][Diffusion] Refactor prompt updates into a modality-ready interaction framework (#6294 )

2026-09-07 11:40:04 +08:00

layers

[Diffusion] Fuse Qwen-Image-Edit select01 modulation for CUDA (#5921 )

2026-09-16 19:06:28 +08:00

lora

[Refactor][Diffusion] Remove model-specific names from LoRA and ModelOpt loader defaults (#5907 )

2026-09-12 20:30:03 +08:00

model_loader

[Hardware][Ascend] Add Wan2.2 MXFP4 UOS, Smooth and W4A8 fallback (#7210 )

2026-09-17 03:11:40 +00:00

models

[Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610 )

2026-09-17 08:41:52 +00:00

offloader

[Refactor][Diffusion] Complete generic backend plan consumption (#7313 )

2026-09-15 08:40:04 +08:00

postprocess

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

profiler

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

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

quantization

[Bugfix] Fix HSDP compatibility with the new online FP8 linear method (#5677 )

2026-08-14 15:45:55 +08:00

sched

[Bugfix][Diffusion] Include guidance_scale_2_provided in the request-batch key (#7078 )

2026-09-07 15:58:19 +08:00

utils

[3/N] Encode streamed video on the worker with bounded batching (#7018 )

2026-09-12 20:58:11 +08:00

worker

[Perf][Cosmos3] Add SeaCache support for Cosmos3 (#6922 )

2026-09-15 14:57:15 -07:00

__init__.py

[Diffusion] Qwen image support (#82 )

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

compile.py

fix: keep DLO hooks outside regional compilation (#6073 )

2026-08-22 21:44:03 +08:00

config.py

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

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

data.py

[Hardware][Ascend] Add Wan2.2 MXFP4 UOS, Smooth and W4A8 fallback (#7210 )

2026-09-17 03:11:40 +00:00

diffusion_engine.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

envs.py

[Kernel][Boogu-Image] Fuse Q/K RMSNorm + interleaved RoPE via fused_qk_norm_rope (#6982 )

2026-09-13 09:39:27 +08:00

forward_context.py

[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (#5717 )

2026-09-06 16:23:30 +08:00

inline_stage_diffusion_client.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

io_support.py

[Feature] Support text encoder Disaggregation for H3 (#5885 )

2026-08-28 14:27:05 +08:00

ipc.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

media.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

model_metadata.py

[Bugfix][Model] Fix FLUX.2 Klein multi-image edit metadata (#7430 )

2026-09-11 14:18:07 +00:00

output_formatter.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

registry.py

[Model] Add Tencent AuK speech generation and editing (encoder + diffusion pipeline) (#7385 )

2026-09-11 20:09:58 +00:00

request.py

[Diffusion] Implement paged AR↔DiT KV connector ("v1", reusing vllm's native mooncake) (#6310 )

2026-09-06 05:41:54 +08:00

stage_diffusion_client.py

[Diffusion] Implement paged AR↔DiT KV connector ("v1", reusing vllm's native mooncake) (#6310 )

2026-09-06 05:41:54 +08:00

stage_diffusion_proc.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

vllm_config.py

[Diffusion] Implement paged AR↔DiT KV connector ("v1", reusing vllm's native mooncake) (#6310 )

2026-09-06 05:41:54 +08:00