anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
2,123 Commits 235 Branches 31 Tags
6d39fb25aa6ae5c3820830c6c43bffe77017292c
Commit Graph
608 Commits
Author SHA1 Message Date
tzhouamandClaude Fable 5 35a423c9bd [BugFix][CI] Address review follow-ups from v0.24.0 rebase (#4709) 
Addresses Gaohan123's post-approval review comments on #4709:

- pipeline_dreamzero: restore platform-dispatched synchronize() instead of
  torch.cuda so DreamZero keeps working on non-CUDA hardware (regression
  of #4399 introduced during the rebase).
- omni_scheduler_mixin: drop the VLLM_OMNI_INPUT_WAIT_TIMEOUT_S env-var
  override; the full-payload input-wait timeout is now a plain constant.
- diffusion_worker: implement _DiffusionVllmModelConfig.is_diffusion by
  mirroring upstream ModelConfig.is_diffusion (dLLM canvas_length check)
  and document why omni DiT pipelines must not enable dLLM paths.
- qwen3_tts: make _embedding_dtype a class attribute on the talker and
  prompt-embeds builder so __new__-based test stubs inherit it; remove
  the (duplicated) manual assignments from the preprocess test.
- .buildkite: document why the rebase raised per-step timeouts (steps
  were killed by the old limits, masking real failures; e.g. CustomVoice
  passes in ~9-15 min but cold runs were killed at 20m).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-07-02 07:36:14 +00:00
Jiaqian Liu a25636d780 [NPU] Fix HunyuanImage3 MoE EP+SP parallel mapping (#4344) 
Signed-off-by: Celeste-jq <591998922@qq.com>
 2026-07-02 04:14:12 +00:00
Thanaji Rao Thakkalapelli 1788d76eb3 [Feature] Improve diffusion LoRA compatibility for SDXL (#4825) 
Signed-off-by: Thanaji Rao Thakkalapelli <thanaji.rao.thakkalapelli@intel.com>
 2026-07-01 23:41:16 +00:00
Alex BrooksandDidan Deng d526dc93e8 [Fix]: Set .transformer on SenseNova pipeline, warn if no .transformer in CacheDiT summary (#4326) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-07-01 17:40:07 +00:00
Zhou Taichang a560ed184d [Rebase] Rebase to vllm v0.24.0 (#4709) 2026-06-30 19:41:06 +08:00
fywcandprincepride 9a105bf90d [Feat] Support teacache for SenseNova-U1 (#4164) 
Signed-off-by: hanzheli <hanzheli@kuaishou.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
 2026-06-30 09:24:46 +00:00
SYLAR bb8614595d [BugFix][Cosmos3] Pad sound latents so video+sound runs under sequence parallelism (#4678) 
Signed-off-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>
Signed-off-by: lishunyang <lishunyang12@163.com>
 2026-06-30 17:23:36 +08:00
boatman 4028680b7e [Perf]: Fused RMSNorm+3D Rope kernel in Sensenova-U1 (#4669) 
Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>
 2026-06-30 16:32:47 +08:00
Yi LiuandCopilot 99234881f5 [Quant][AutoRound] Add W4A16 support for Qwen-Image (#3588) 
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
 2026-06-30 16:27:28 +08:00
boatmansphinxkkkbc汪志鹏
 		dd3a4d0a29 [Feat] Support CFG-Parallel For Sensenova-U1-8B-MoT (#4188) 
Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-06-30 08:03:26 +00:00
Mohammed Saif AbedandClaude 2fc00efa49 [Model] Migrate MammothModa2-Preview example to standard task example + model_extras (#4691) 
Signed-off-by: mo saif <moisf56@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-30 04:34:06 +00:00
JiangJie ZhangandSamit c45ac74d43 [Core][Frontend] Support request-level batching for diffusion pipelines (#4079) 
Signed-off-by: jader <yjader@foxmail.com>
Co-authored-by: Samit <285365963@qq.com>
 2026-06-29 18:09:19 +02:00
SuyanLiandsuyan.li 1b318d11d1 [Refactor] Reuse CFGParallelMixin in Bagel for CFG-parallel denoising (#4768) 
Signed-off-by: suyan.li <suyan.li@bytedance.com>
Co-authored-by: suyan.li <suyan.li@bytedance.com>
 2026-06-28 07:16:10 +00:00
Chendi.Xue 60ccadfbb6 [WAN_S2V] Enable HSDP for wan s2v (#4458) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
 2026-06-28 06:27:58 +02:00
Rahul SteigerandHongsheng Liu 327e9dcaf2 [Feature] Spatially-sharded (SP) decode for the Wan VAE (#4620) 
Signed-off-by: Rahul Steiger <rsteiger@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-27 09:01:25 +08:00
MaciejBalaNV 47871d5e20 Updated Cosmos3 docstrings (#4727) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
 2026-06-27 06:39:42 +08:00
bmengkeandHongsheng Liu 329c98ff9d Wan2.2: Fix the bug of using cache-dit with ulysses in t2v and i2v (#3927) 
Signed-off-by: Mengkejiergeli Ba <mengkejiergeli.ba@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-25 15:15:59 +00:00
Honghan ZhuClaude Opus 4.7zhuhh97
 		5db89b41c4 [Core] hunyuan-image prefetch kv (#4448) 
Signed-off-by: z00806815 <zhuhonghan@huawei.com>
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Signed-off-by: zhh <zhh@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: zhuhh97 <zhuhh97@users.noreply.github.com>
 2026-06-25 21:31:49 +08:00
Wang fuyinzwhzzz0821Hongsheng Liu
 		8ddcb3621f [Config] Add structured VllmOmniConfig classes (#4425) 
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Signed-off-by: Wang  fuyin <wfy2003324@163.com>
Co-authored-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-25 17:48:20 +08:00
Daniel SocekandDidan Deng fb563fbd19 [Bugfix] Fix CFG-parallel broadcast dtype mismatch in GLM-Image (#3956) 
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-06-25 13:14:29 +08:00
Jiantong MenmenjiantongDidan Deng
 		0fd2620d56 [BugFix] Fix MammothModa2 Text-to-Image Bug (#4299) 
Signed-off-by: menjiantong <menjiantong@foxmail.com>
Co-authored-by: menjiantong <menjiantong@foxmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-06-25 13:14:02 +08:00
WeiQing ChenandIanniu d94108693a [BugFix] Fix Wan2.2-VACE-Fun cache and serving lifecycle (#4667) 
Signed-off-by: Ianniu <985683179yzy@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Ianniu <985683179yzy@gmail.com>
 2026-06-25 11:20:58 +08:00
bjf-frz d612233bef [Bugfix][CI]Fix HSDP regional compile boundary (#4668) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
 2026-06-25 02:52:52 +00:00
Yuanheng Zhao fb3abb38fb [refactor] Flatten Ming-flash-omni-2.0 imagegen args (#4587) 
Signed-off-by: Yuanheng <jonathan.zhaoyh@gmail.com>
 2026-06-24 17:01:58 +08:00
Chendi.Xue eb81914c64 [S2V] Add sequence parallelism support to WanS2VTransformer3DModel (#4276) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
 2026-06-24 14:04:04 +08:00
MrDongslsMr.DongYueqian LinYueqian Lin
 		1951dca786 [Model] add soulx-singer support (#3862) 
Signed-off-by: Mr.Dong <1042542469@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Mr.Dong <1042542469@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
 2026-06-24 05:36:45 +00:00
MaciejBalaNVandHongsheng Liu 6dc4638a7e Fixed Cosmos3 regression (#4627) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-24 09:03:34 +08:00
Zeyu Huang | 黃澤宇Copilot Autofix powered by AICursor
 		3901ad8165 [feat] Streaming diffusion video generation output (#3737) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-23 09:57:53 +00:00
Y. Fisher 64efa66869 [NPU] Initialize Ascend config for diffusion workers (#4386) 
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
 2026-06-23 03:12:44 +00:00
Nick CaoandClaude 6646a66d41 [BugFix] Use ModuleDiscovery for HSDP DiT sharding to support nested pipelines (#3456) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-23 02:54:14 +00:00
bjf-frz 2447740308 [Perf]perf: skip unused Cosmos3 I2V conditioning latents (#4614) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
 2026-06-22 09:51:47 +00:00
汪志鹏 a10eac0f8c [Feature]: Migrate magi human example (#4572) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-06-22 15:17:00 +08:00
WeiQing ChenandHongsheng Liu f0d7fe18f2 [Perf][Cosmos3] Optimize I2V conditioning transfer (8.63% faster x-inference) (#4467) 
Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-22 01:59:03 +00:00
Alex Brooksand汪志鹏 7ff11d8d0f [Perf/Fix] Reimplement Batched CFG Forward for Bagel (#4098) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-06-22 07:37:21 +08:00
MaciejBalaNVandHongsheng Liu fc32d9fe6f Improve Cosmos3 v2v quality (#4514) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-21 22:20:30 +08:00
Shin 1292c47804 [BugFix]Fix diffusion profile RPC None results (#4372) 
Signed-off-by: yixiaoer <shin@yixiaoer.sg>
 2026-06-21 17:14:21 +08:00
MaciejBalaNV a1e1ac0155 Cosmos3 transfer (#4379) 
Signed-off-by: Maciej Bala <mbala@nvidia.com>
Signed-off-by: MaciejBalaNV <mbala@nvidia.com>
 2026-06-21 09:59:18 +08:00
Zhengyuan Su (苏政渊)andClaude Opus 4.8 2d0b1d8a29 [Diffusion] add GR00T-N1.7 pipeline with OpenPI serving (#3798) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-20 11:45:26 +08:00
TJian e70822ed54 [ROCm] [CI] Fix diffusion test (#4574) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-06-20 08:31:39 +08:00
Alex Brooks 6ff246bf3c [Cache Refactor 1/N] Simplify CacheDiT Integration (#2527) 
Signed-off-by: Alex Brooks <albrooks@redhat.com>
 2026-06-20 08:30:44 +08:00
Kwokho TsuiandKwokho Tsui 7e152ca64b [Bugfix] Fix HSDP + FP8 online quantization compatibility (#4494) 
Signed-off-by: Kwokho Tsui <kh_tsui@163.com>
Co-authored-by: Kwokho Tsui <kh_tsui@163.com>
 2026-06-19 15:06:27 +08:00
amy-why-3459 f05e03aea8 [Perf][DreamZero]dreamzero supports CUDA graph, torch.compile, and DiT Caching. (#4213) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-06-19 14:24:37 +08:00
yangyonggit 37a442447e [Cleanup] Remove duplicate HiDreamI1ImagePipeline (fixes #4009) (#4045) 
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
 2026-06-19 06:32:18 +08:00
Honghan Zhu 8f28b969e9 [Feat] DreamZero fix tp & cross attn cache (#4154) 2026-06-18 10:57:04 +00:00
汪志鹏CursorHongsheng LiuClaude Sonnet 4.6
 		f75c437a60 [Refactor]Base class for dit pipelines with unified parameter declaration[1/N] (#4225) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-18 17:14:18 +08:00
bjf-frz 14d70d9870 [Perf]Enable regional compile for Cosmos3 HSDP blocks (#4485) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
 2026-06-18 16:54:05 +08:00
汪志鹏 f195e44bc1 [BugFix]: Fix Bagel generate_image denoising schedule (#4509) 2026-06-18 02:02:38 +00:00
Nick CaoandClaude e957d16f8d [Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-17 21:33:06 +08:00
KristofferandHongsheng Liu 890803ca06 [Wan2.2] Fix "uninitialized nn.Module of type RotaryEmbeddingWan" graph-break (#4053) 
Signed-off-by: Kristoffer Torp <kristoffer.torp@amd.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-17 15:48:22 +08:00
Peiqi YinHongsheng LiuChenguang ZHENG
 		64a5bb92de [Refactor] Omni Stage Runtime and Distributed Replica Control Plane (#3855) 
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
 2026-06-17 14:13:20 +08:00