anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
3,228 Commits 235 Branches 31 Tags
44ea27c8094095bbffd88fa3befdfaa55ba4bc50
Commit Graph
247 Commits
Author SHA1 Message Date
Isotr0py be8a72f0a6 Stack torch.compile with CUDA graph decode instead of choosing one 
Regionally compile the DiT blocks even when enable_cuda_graph_decode is set
and let graph capture record the compiled (fused) kernels; inductor's own
cudagraphs stay off so the two graph layers never nest. Measured on GB200
(1024x1024, 50 steps, seed 42, BF16): combo 3.04s vs compile-only 3.2s,
graph-only 4.0s, eager 4.3s per image; 44.5-45.6 dB PSNR vs eager.
 2026-09-22 08:58:32 +00:00
Isotr0py 3e274a0024 Merge remote-tracking branch 'origin/main' into qwen-image-2.1 
# Conflicts:
#	tests/entrypoints/openai_api/test_image_server.py
#	vllm_omni/entrypoints/openai/api_server.py
 2026-09-22 01:23:45 +00:00
Sy03 60a933b9ab [Model] Default Qwen3-TTS to experimental Model Runner V2 (#7930) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-21 18:56:06 +00:00
tsinghua-code e5c0afc994 [Model] Enable online FP8 linears for LingBot World (#7549) 
Signed-off-by: tsinghua-code <zr-liu25@mails.tsinghua.edu.cn>
 2026-09-21 12:21:46 +00:00
wtz2333 8efd3c2f6d [Feature] Add experimental LingBot World last-step KV reuse (#7816) 
Signed-off-by: wtz2333 <2955110911@qq.com>
 2026-09-21 17:02:15 +08:00
Isotr0py 3d6a1c4d9a Address review: examples policy, SPDX headers, recipe docs, test coverage 
- Register QwenImage21Pipeline in model_extras _EXTRA_SPECS with an
  image-to-image prompt builder that forwards height/width
- Rename run_qwen_image_21_edit.sh to run_qwen_image_21.sh
- Fix SPDX-FileCopyrightText headers
- Recipe: document mixed-KV-phase admission, add head-vs-diffusers A/B
  comparison section (measurements pending)
- Add test_registry.py and test_pipeline.py (preprocess, prepare_latents
  ordering, mixed-phase _assemble_kv_cache, post-process); extend
  test_batch_compatibility.py
 2026-09-21 08:36:42 +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
Ding ZuhaoandCursor 154a1f25f5 [Bugfix] Honor the requested output canvas in BAGEL img2img (#7287) 
Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-21 07:29:24 +00:00
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
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
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
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
yulun b6b868f3de [Hardware][Ascend] Enable VoxCPM2 eager optimizations (#7207) 
Signed-off-by: Big2Wheel <1404207590@qq.com>
 2026-09-20 11:18:12 +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
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
Isotr0py 47e6acc1e3 Add FP8 KV cache support for Qwen-Image-2.1 DiT (#7797) 2026-09-19 00:06:58 +08:00
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
Tianyu Guo ab4cf24b3e Optimize Qwen-Image 2.1 attention and decode graph reuse (#7790) 
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
 2026-09-18 19:37:19 +08:00
Tianyu Guo b0a309e5e7 Isolate Qwen-Image 2.1 prefill and decode scheduling (#7770) 
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
 2026-09-18 14:11:22 +08:00
Isotr0py 3affc7766d Enable VAE tiling for Qwen-Image-2.1 (#5) 
* init

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix

Signed-off-by: Isotr0py <mozf@inferact.ai>

* test(diffusion): add Qwen-Image-2.1 unit tests

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix(diffusion): Qwen-Image-2.1 VAE spatial ratio, tiling e2e verification

- AutoencoderKLQwenImage21: derive spatial_compression_ratio from the
  architecture (2 ** len(temperal_downsample) = 16x) instead of trusting
  the checkpoint's scale_factor_spatial=8, which corrupted tiled
  decode/encode geometry (output cropped to half size) and tiling gating.
- pipeline: _read_vae_scale_factor prefers the architecture-derived value
  for the same reason.
- models/qwen_image_21/__init__: lazy exports to break the circular import
  distributed VAE -> package __init__ -> pipeline -> distributed VAE.
- Add VAE unit tests: ratio derivation, tiled vs untiled decode/encode
  consistency, distributed tile_split/exec/merge == tiled_decode.
- e2e matrix (GB200, seed 42, 20 steps) all green; see e2e_out/qwen21_vae/.
- examples: qwen_image_21_edit.py gains --vae-use-tiling.
- docs: mark VAE patch-parallel verified for Qwen-Image-2.1; recipe notes
  the default-tile banding limitation at 2048px+.

* clean tests

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix cudnn determination

Signed-off-by: Isotr0py <mozf@inferact.ai>

---------

Signed-off-by: Isotr0py <mozf@inferact.ai>
 2026-09-18 10:02:50 +08:00
Chenchao Xu d0755b5716 [Model] Add π0.5 (Pi0.5) VLA model support (#6950) 
Signed-off-by: chenchaox <chenchaox@nvidia.com>
 2026-09-17 05:18:51 -07:00
ooooooye 873e9bff7c [Doc][NPU] Refresh MiniMax-H3 Ascend recipes for 0.28-era configurations (#7720) 
Signed-off-by: brandneway <gyuan4892@gmail.com>
 2026-09-17 11:05:15 +00:00
WeiQing Chen cb439f3e84 [Diffusion][Model] Add direct FastH3 8-Step V2 checkpoint loading (#7610) 
Signed-off-by: david6666666 <530634352@qq.com>
 2026-09-17 08:41:52 +00:00
Bojiang Li d81777f297 [Doc] Scope Spark FP8 guidance to the validated revision (#7536) 
Signed-off-by: bojiang-li <327132355+bojiang-li@users.noreply.github.com>
 2026-09-17 08:30:47 +08:00
Yueqian Lin 5aadcbb0ab [Bugfix] Fix Breeze-TTS-2 repeated silence and audio EOS handling 2026-09-16 18:40:12 +00:00
Wu JIAZHENJaderHongsheng Liu
 		d554e6b67e [feat] Extend disaggregated MiniMax-H3 stage with VAE encoders (#6939) 
Signed-off-by: asukaqaq-s <1311722138@qq.com>
Signed-off-by: Jader <yjader@foxmail.com>
Co-authored-by: Jader <yjader@foxmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-16 16:52:35 +08:00
Linze Shi e78a5d01f7 [Frontend] Add MiniMax-H3 references and Ref2VA workflow (#7483) 
Signed-off-by: Linze-Shi <linzeshi0@gmail.com>
 2026-09-16 08:30:16 +00:00
chickeytonandClaude Opus 5 99ff4f3070 [Core][Frontend] Unified Full-duplex Framework (#7413) 
Signed-off-by: chickeyton <ngton2014@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
 2026-09-16 15:35:36 +08:00
Isotr0py 2912672b2e Initialize QMI pipeline implementation (#2) 
* init

Signed-off-by: Isotr0py <mozf@inferact.ai>

* fix

Signed-off-by: Isotr0py <mozf@inferact.ai>

---------

Signed-off-by: Isotr0py <mozf@inferact.ai>
 2026-09-16 15:14:23 +08:00
Clodagh Walsh a1a234a0b4 [Voxtral] Raise BadRequest for ref_audio (#7012) 
Signed-off-by: Clodagh Walsh <clodaghwalsh17@gmail.com>
 2026-09-15 18:26:08 -07:00
yzhautouskay 6040bb97e2 [Perf][Cosmos3] Add SeaCache support for Cosmos3 (#6922) 
Signed-off-by: Yuliya Zhautouskaya <yzhautouskay@nvidia.com>
 2026-09-15 14:57:15 -07:00
wtz2333 a3dee6fdf5 [Lingbot World] Bound image condition storage and extend temporal RoPE (#6838) 
Signed-off-by: wtz2333 <2955110911@qq.com>
 2026-09-15 18:49:55 +08:00
yulun 8e088c7725 [Hardware][Ascend][Model] Support MOSS-TTS-Nano on Ascend A2 (#7192) 
Signed-off-by: Big2Wheel <1404207590@qq.com>
 2026-09-14 15:25:17 -07:00
LOGO127 7ad51f0007 [Misc][HiggsAudioV3] Diagnose skipped reference audio substitution (#7098) 
Signed-off-by: luozijian <luozijian0924@gmail.com>
 2026-09-14 15:24:49 -07:00
heyuanliu-intel 40f8e94400 [Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047) 
Signed-off-by: heyuanliu-intel <heyuan.liu@intel.com>
 2026-09-14 10:02:30 -07:00
nonamenonameYueqian Lin
 		ea1a416a17 [Model] Add Breeze-TTS-2 two-stage AR TTS support (talker + codec, streaming) (#7084) 
Signed-off-by: noname <liuzhiwei08@kuaishou.com>
Signed-off-by: noname <133508552+lzwnoname@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: noname <liuzhiwei08@kuaishou.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-09-14 09:55:53 -07:00
jiahengxie 2cbfd3e93b [Performance][MammothModa2] Enable and validate FP8 KV cache for AR stage (#7436) 
Signed-off-by: JH <13716265422@139.com>
 2026-09-14 00:47:39 -07:00
Lei KeandKrystalRay 6505577459 [Doc][NPU] Keep AllGather for MiniMax-H3 INT8 DLO (#7444) 
Signed-off-by: KrystalRay <keeleiray@gmail.com>
Co-authored-by: KrystalRay <keeleiray@gmail.com>
 2026-09-14 06:20:59 +08:00
Hongsheng Liuandamy-why-3459 01a2f93256 [Bugfix][Frontend] Honor output_compression on the image generations route (#7447) 
Signed-off-by: hsliu_ustc <hsliu_ustc@noreply.gitcode.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-09-13 10:05:56 +08:00
Yueqian LinandSy03 c111f3a2d6 [Model] Add Tencent AuK speech generation and editing (encoder + diffusion pipeline) (#7385) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Sy03 <1370724210@qq.com>
 2026-09-11 20:09:58 +00:00
SuyanLiClaude Opus 4.8suyan.liHongsheng Liu
 		a7ab91fb85 [Example] Migrate HunyuanImage-3.0 to model_extras + shared task examples (#5559) 
Signed-off-by: suyanli220 <suyanli220@gmail.com>
Signed-off-by: suyan.li <suyan.li@bytedance.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: suyan.li <suyan.li@bytedance.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-11 16:47:25 +08:00
MaciejBalaNVandHongsheng Liu 05ab509269 Cosmos3 action policy improvements (#6460) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Signed-off-by: MaciejBalaNV <mbala@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-09-10 22:32:50 +08:00
wkutakandRahul Steiger 43a476c1e5 [Model] Add Cosmos3 mixed W8A8/W8A16 and W4A4/W4A16 denoising (#6560) 
Signed-off-by: Rahul Steiger <rsteiger@aws-cmh-slurm-1-vscode-04.cm.cluster>
Signed-off-by: Wojciech Kutak <wkutak@nvidia.com>
Co-authored-by: Rahul Steiger <rsteiger@nvidia.com>
 2026-09-10 23:51:09 +12:00
Sy03 333f14e97e [Bugfix][MiniCPM-o] Align structured chat content with native omni rendering (#7344) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-10 11:38:11 +08:00
Sy03 b02862beee [Model] Optimize MOSS-TTS Local batched execution and streaming codec (#7202) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-09-09 13:02:12 -07:00
bojiang-li 504e5a6a6e [Doc] Add dual DGX Spark MiniMax-H3 results (#7343) 
Signed-off-by: bojiang-li <327132355+bojiang-li@users.noreply.github.com>
 2026-09-09 18:48:41 +00:00
NumberWan 038c9b948f [Bugfix] Resolve #6931 hub FA3 on torch 2.13 via kernels 0.16.1 (#7185) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-09-09 10:20:34 +00:00
chi030303 c66df06c0f [Doc] Qwen3-TTS: add 0.6B on 1x A100 40GB (#7289) 
Signed-off-by: chi030303 <106855944+chi030303@users.noreply.github.com>
 2026-09-09 07:56:14 +00:00
Sparks 7712701578 [Doc] [Recipe] Add FLUX.1-schnell recipe for RTX 5090 32GB (#7299) 
Signed-off-by: Sparks-M <41097544+Sparks-M@users.noreply.github.com>
 2026-09-09 07:54:46 +00:00