anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
3,192 Commits 235 Branches 31 Tags
d3cf26c1b1cf942e23e07ecaed0840e2c090658a
Commit Graph
3192 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Isotr0py d3cf26c1b1 Wire enable_cuda_graph_decode through engine args, stage config and CLI 
Follows the vae_use_tiling path: OmniDiffusionConfig field, OmniEngineArgs,
StageDeployConfig, _DiffusionConfigProjection and --[no-]enable-cuda-graph-decode.
Documents interplay with enforce_eager and cudagraph_mode.
 2026-09-21 08:36:34 +00:00
Isotr0py a04b95bf6b Address review: tuple image input, NPU index_select rope, per-key decode graph ownership 
- Normalize tuple image inputs in pre_process_func (empty tuple -> T2I path)
- Use torch.index_select in QwenImage21Rope for NPU compatibility (#6320 style)
- Refuse concurrent aliasing of shared decode-graph prefix KV entries: track a
  single live owner per key, non-owners fall back to eager decode
 2026-09-21 08:36:28 +00:00
Isotr0py 9174554e40 Merge remote-tracking branch 'origin/main' into qwen-image-2.1 
# Conflicts:
#	vllm_omni/diffusion/executor/multiproc_executor.py
#	vllm_omni/diffusion/offloader/sequential_backend.py
 2026-09-21 07:32:04 +00:00
Zhou TaichangandClaude Fable 5.1 86fcfe95f1 [LingBot World] Eleven bit-identical removals of repeated work in the realtime path (#7648) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
 2026-09-21 06:12:45 +00:00
Sy03 a9e2117f5e [Core][Model] Enable Qwen3-TTS MRV2 and optimize the TTS pipeline (#7781) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-20 23:03:08 -07:00
DMAN d139c600c7 [Model] Add online FP8 support for Boogu-Image MLLM (#7342) 
Signed-off-by: Dmaner <2663515256@qq.com>
 2026-09-21 05:13:37 +00:00
Abhinav Raichur 1b87115c9e feat(comfyui): add MiniMax H3 first and last frame inputs (#7449) 
Signed-off-by: avraichur96 <avraichur96@gmail.com>
Signed-off-by: Abhinav Raichur  <avraichur96@gmail.com>
 2026-09-21 10:24:25 +08:00
Wallbreazzzamy-why-3459Gao Han
 		ae3880f0e3 [Performance] Capture MOSS-TTS codec streaming decode with NPUGraph (#7280) 
Signed-off-by: Wallbreazzz <110282866+Wallbreazzz@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-09-21 06:38:23 +08:00
Zeyu Huang | 黃澤宇 e36babd48f [Core][Diffusion] Camera interaction for diffusion streaming generation (LingBot World 2 as example) (#7198) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
 2026-09-20 16:19:41 +00:00
汪志鹏 139a47a578 [Model] Add MiniMax-H3 long-video latent continuation with driving audio (#7838) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-09-20 23:44:33 +08:00
DanaerLeeandzijianc2 16734bbdf3 [Bugfix] Route text-only chat as per-request comprehension in HunyuanImage3 AR sampler (#6111) 
Signed-off-by: MrlixiangWE <mrdanaer@gmail.com>
Co-authored-by: zijianc2 <157244773+zijianc2@users.noreply.github.com>
 2026-09-20 15:23:53 +00:00
Wu JIAZHENAcerak01-fyamy-why-3459
 		102ba716bf [Feat] Add native Mooncake KV transfer from AR to DiT (#7166) 
Signed-off-by: asukaqaq-s <1311722138@qq.com>
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-20 14:44:55 +00:00
psv666 2d0b03f717 [Bugfix] Fix Qwen3-Omni realtime playback interruption and conversation history (#7791) 
Signed-off-by: psv666 <2693925048@qq.com>
 2026-09-20 14:42:17 +00:00
RyanYun09 d3396fc5fb # [Bugfix] Replace ffmpeg subprocess with PyAV to avoid HEVC decoder hang (#7364) (#7504) 
Signed-off-by: RyanYun09 <318555231+RyanYun09@users.noreply.github.com>
 2026-09-20 14:37:09 +00:00
Canlin Guo 4d877780d3 [Bugfix] Avoid waveform-list GC scans and release completed MOSS batches (#7885) 
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-09-20 05:36:52 -07:00
jingchengtianHongsheng Liuamy-why-3459
 		23f4126445 [Hardware][Ascend] Use incremental KV-cache decode for MOSS-TTS depth transformer (#6967) 
Signed-off-by: jingchengtian <tjc1995@126.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-20 18:34:25 +08:00
AliciaandHongsheng Liu d02681bf01 [Refactor][Diffusion] Move single-model layers into their model directories (#5908) 
Signed-off-by: congw729 <115451386+congw729@users.noreply.github.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-20 18:19:24 +08:00
amy-why-3459 9f5521351e [Benchmark][MiniCPM-o] Port Video-MME dataset support to Omni bench s… (#6987) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-20 17:15:53 +08:00
tlysanhuo ea62f86718 [Bugfix] Honor request-level seed in VoxCPM2 CFM noise (#7866) 
Signed-off-by: tly <2200895168@qq.com>
 2026-09-20 16:24:38 +08:00
wangyuandYueqian Lin 6a03e45c34 [Misc] Remove Dynin-Omni and dots.tts support (#7655) 
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-20 00:28:29 -07:00
Zeng Chuang 3f94c417be [Bugfix] Stabilize NIXL ownership test claim queries (#7870) 
Signed-off-by: zengchuang-hw <zengchuang1005@gmail.com>
 2026-09-20 06:55:47 +00:00
Tianyu Guo 3ea9e60501 Fix diffusion API initialization (#7868) 
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
 2026-09-20 12:08:50 +08:00
xiaoyu-xyz 5a93ec1b4e [Model][Frontend] MiniMax-H3: Add latent-mask editing (#7465) 
Signed-off-by: xiaoyu <1259084489@qq.com>
 2026-09-20 03:54:44 +00:00
Tianyu Guo 9dabaf8b80 Default Qwen-Image 2.1 CFG scale to 1.0 (#7859) 
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
 2026-09-20 11:51:35 +08:00
汪志鹏 8e10c3ee07 [Bugfix] Avoid multimodal cache collisions in multistage image editing (#7817) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-09-20 11:27:06 +08:00
yulun b6b868f3de [Hardware][Ascend] Enable VoxCPM2 eager optimizations (#7207) 
Signed-off-by: Big2Wheel <1404207590@qq.com>
 2026-09-20 11:18:12 +08:00
ooooooyeandWeiQing Chen b2b6c6c7a9 [Perf][MiniMax-H3] Cut video VAE encode/decode memory peaks for low-memory serving (#7241) 
Signed-off-by: brandneway <gyuan4892@gmail.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
 2026-09-20 10:56:54 +08:00
ooooooye a9abd563f9 [Bugfix][RAINFUSION_ATTN] Fix padding-mask rejection on packed [real, pad] layouts and reuse query tail as output padding (#7235) 
Signed-off-by: brandneway <gyuan4892@gmail.com>
 2026-09-20 10:56:51 +08:00
andyluo7 fa422a3f44 [CI/Build][ROCm] Cache AMD test images in registry (#7712) 
Signed-off-by: andyluo7 <andy.luo@amd.com>
 2026-09-20 09:51:14 +08:00
chethanukandGao Han 573ec4cdac fix(e2e): re-point HunyuanImage3 offline test to text_to_image.py (#7525) 
Signed-off-by: ChethanUK <chethanuk@outlook.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-09-19 11:16:13 -07:00
leegangtoe fa506e0fe8 [Bugfix] Register statistics for dynamically added replicas (#7298) 
Signed-off-by: leegangtoe <leegangtoe@gmail.com>
 2026-09-19 17:07:14 +00:00
Inesh Reddy Chappidi 51c715c7ef [Bugfix][Test] Assert stable-audio CPU offload savings on max_memory_allocated (#6826) 
Signed-off-by: Inesh Reddy <ineshreddy249@gmail.com>
Signed-off-by: Inesh Reddy Chappidi <ineshreddy249@gmail.com>
 2026-09-19 10:04:58 -07:00
NumberWan 23d8c83dab [Bugfix][Qwen-Image] Keep AutoRound W4A16 on CPU when offloading; Fixes #7555 (#7579) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-09-19 16:34:11 +00:00
boatman f9f53f2bd8 [Bugfix]Include Reference Audio Cache Salt for HiggsAudio v2 (#7826) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-09-20 00:19:14 +08:00
akshatvishu 415005be22 [Model] Add circlestone-labs/Anima (#4083) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-09-19 16:16:38 +00:00
TaffyOfficialTaffyOfficialGao Han
 		698f716012 [Refactor] Reject unknown diffusion config fields (#5172) 
Signed-off-by: TaffyOfficial <2324465096@qq.com>
Signed-off-by: zuiho <2324465096@qq.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: TaffyOfficial <2324465096@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-09-19 15:37:34 +00:00
psv666andamy-why-3459 f90c267ffb [Bugfix] Use monotonic clocks for test server startup timeouts (#7628) 
Signed-off-by: psv666 <2693925048@qq.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-19 21:25:14 +08:00
Zheng Wengangamy-why-3459Hongsheng Liu
 		470ec60848 [Core] Refactor omni prefix cache into Manager/Controller (#6654) 
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-19 21:23:59 +08:00
Anjie HouClaude Opus 5Hongsheng Liu
 		ea84055507 [Refactor][Diffusion] Resolve distributed layerwise topology in the plan (#7326) 
Signed-off-by: specture724 <specture724@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-19 19:05:18 +08:00
andyluo7 232dbc82f8 [CI/Build] Restrict ERNIE fused RoPE tests to NVIDIA CUDA (#7771) 
Signed-off-by: andyluo7 <andy.luo@amd.com>
 2026-09-19 13:23:50 +08:00
Joshna-Medisetty 4c7a98c26f [XPU][CI] Drop the USTC PyPI mirror from the XPU image build (#7808) 
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
 2026-09-18 17:32:33 -05:00
Sunamy-why-3459Yueqian Lin
 		7b4fc7ce2e [Model] Migrate MammothModa2 DiT to the shared diffusion runtime (#7134) 
Signed-off-by: levius <2114377220@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-18 13:29:18 -07:00
Joshna-MedisettyandCursor ca3ccfc9a3 [XPU][Bugfix] Make AR-Diffusion KV preallocation device-agnostic (#7777) 
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-18 14:41:41 -05:00
bcsdhjew fbb4e63f0a [Bugfix][Core] Apply Realtime item truncation once per command (#7800) 
Signed-off-by: Nolen Liang <nliang@nvidia.com>
 2026-09-18 18:59:09 +00:00
Yueqian Lin 0570f7a06e [CI][Qwen3-Omni] Keep the deploy-YAML literal in the structured-config sampling check (#7803) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-18 18:25:01 +00:00
Isotr0py 5b540f55d3 Fix decode cuda graph for Qwen-Image-2.1 model-level cpu offload (#7801) 2026-09-19 00:10:53 +08:00
Isotr0py 47e6acc1e3 Add FP8 KV cache support for Qwen-Image-2.1 DiT (#7797) 2026-09-19 00:06:58 +08:00
Yueqian Lin d4ffde1a6e [CI][Qwen3-Omni] Compare structured-config sampling defaults against vLLM normalization (#7742) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-18 14:55:58 +00:00
Isotr0py 2a92b71cb9 Add FP8 online qunatization support for Qwen-Image-2.1 (#7792) 
Signed-off-by: Isotr0py <mozf@inferact.ai>
 2026-09-18 22:33:16 +08:00
wangyuandCursor 0a5ece4ae5 [CI/Build] Retarget skipped HiDream and MammothModa2 E2E tests to current issues (#7755) 
Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-18 13:24:00 +00:00