Wenjia LiandHongsheng Liu 38a2500bdf [Perf] MiniMax H3 Qwen3-VL support fused RMSNorm on NPU (#5915) ...

Signed-off-by: Wenjia Li <wjialish@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-08-12 19:12:54 +08:00

..

attention

[Bugfix] rainfusion support all shape video (#6000)

2026-08-11 05:10:50 +08:00

cache

[MiniMax-H3] TeaCache support and Cache-DiT validation (#5840)

2026-08-09 15:07:21 +00:00

diffusion_kv

[Diffusion] Add Worker contracts and RPC plumbing for Scheduler-managed paged KV cache (#5550)

2026-08-11 14:55:42 +08:00

distributed

[Bugfix] Fix Wan spatial reshard boundary (#6062)

2026-08-12 11:36:24 +08:00

executor

[Diffusion] Add Worker contracts and RPC plumbing for Scheduler-managed paged KV cache (#5550)

2026-08-11 14:55:42 +08:00

hooks

[Refactor][Misc] Remove unused code in diffusion hooks/model_loader (#5270)

2026-07-22 09:45:17 +08:00

layers

[Bugfix] Fix HunyuanImage3 accuracy test (#5981)

2026-08-12 02:40:05 +00:00

lora

[Feature]: Adds distilled LoRA support for diffusion models (#2783)

2026-08-11 14:23:43 +00:00

model_loader

[NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706)

2026-08-06 14:15:21 +08:00

models

[Perf] MiniMax H3 Qwen3-VL support fused RMSNorm on NPU (#5915)

2026-08-12 19:12:54 +08:00

offloader

feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)

2026-08-06 09:02:29 +08:00

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

[Diffusion] Add Worker contracts and RPC plumbing for Scheduler-managed paged KV cache (#5550)

2026-08-11 14:55:42 +08:00

utils

[Feature]: Adds distilled LoRA support for diffusion models (#2783)

2026-08-11 14:23:43 +00:00

worker

[Feature]: Adds distilled LoRA support for diffusion models (#2783)

2026-08-11 14:23:43 +00:00

__init__.py

[Diffusion] Qwen image support (#82)

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

compile.py

[Rebase] Rebase to vllm 0.27.0 (#5976)

2026-08-11 15:23:46 +00:00

config.py

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

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

data.py

[Feature]: Adds distilled LoRA support for diffusion models (#2783)

2026-08-11 14:23:43 +00:00

diffusion_engine.py

[Diffusion] Add Worker contracts and RPC plumbing for Scheduler-managed paged KV cache (#5550)

2026-08-11 14:55:42 +08:00

envs.py

[Refactor] Extract has_flash_attn_pkg in OmniPlatform (#3068)

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

forward_context.py

[Attention] Refine TRTLLM attention support for MiniMax H3 (#5779)

2026-08-06 09:38:17 +00:00

inline_stage_diffusion_client.py

[Diffusion] Fix DLO DP concurrent request execution (#5864)

2026-08-08 08:24:42 +08:00

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

[Diffusion] Fix DLO DP concurrent request execution (#5864)

2026-08-08 08:24:42 +08:00

model_metadata.py

[Bugfix] Fix image num check error (#5838)

2026-08-07 08:50:24 +00:00

output_formatter.py

[Frontend] Add midway prompt update for streaming video generation (#4652)

2026-07-27 14:07:43 +08:00

prompt_update.py

[Frontend] Add midway prompt update for streaming video generation (#4652)

2026-07-27 14:07:43 +08:00

registry.py

[Model] Add LongCat-Video-Avatar-1.5 ai2v, at2v support (#4099)

2026-08-11 15:17:17 +08:00

request.py

[Diffusion] Prepare HunyuanImage3 for Scheduler-managed paged KV cache (#5541)

2026-08-10 08:48:56 +08:00

stage_diffusion_client.py

[Frontend] Add midway prompt update for streaming video generation (#4652)

2026-07-27 14:07:43 +08:00

stage_diffusion_proc.py

[Refact] Refactor diffusion output streaming (#5166)

2026-07-23 10:06:08 +08:00