anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
2,014 Commits 235 Branches 31 Tags
9678ae58cf5722ceef1f4dfc1b1ebaca5bb9632f
Commit Graph
2014 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Taichang ZhouandClaude Opus 4.8 9678ae58cf [MR V2] Migrate to Model Runner V2 
Squashed migration rebased onto current main. Collapses the 46-commit
dev/migrate-MR-v2 history (10 merge commits + superseded pre-rebase work)
into a single commit, so the diff reflects only the genuine MR-V2 feature
(worker_v2/ runners + model_states, omni schedulers, stage engine pipeline,
pooling_output serialization bridge). Content already merged to main
separately (step_audio2, tts_adapters, npu/_310p, etc.) drops out.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-20 07:19:40 +00:00
Yueqian LinSy03Hongsheng Liu
 		cead615288 [Bugfix][Qwen3-Omni] Fix Code2Wav CUDA-graph output length surplus (#4466) (#4525) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-19 23:58:45 -07:00
Zhengyuan Su (苏政渊) 17cf60a63d [Bugfix] Align vLLM Omni Request input signature with vLLM. (#4568) 
Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
 2026-06-20 04:25:43 +00:00
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
Ian Eaves 951ae28eb0 [Frontend] Configurable video storage backends with TTL (#2531) 
Signed-off-by: Ian Eaves <ian.k.eaves@gmail.com>
 2026-06-19 17:41:22 -06:00
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
Yueqian Lin 208932210f [Chore][TTS] Reference recipes.vllm.ai recipes, remove dead code, and fix stale references (#4567) 
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
 2026-06-19 15:05:26 +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 63ba11b8b1 [Perf] Stacked audio ops: batched matmul and embedding gather in MOSS-TTS talker (#4230) 
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
 2026-06-19 00:38:32 +00:00
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
yangyonggit 13e9094be0 [Doc] Add 1x RTX A6000 48GB section to Voxtral TTS recipe (#2645) (#4051) 
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
 2026-06-19 06:27:26 +08:00
yangyonggitandYueqian Lin 1228a109f0 [Bugfix] MOSS-TTS: fix cross-request audio corruption under batching (#4415) 
Signed-off-by: leo.yang <leo.yang.engineer@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-06-18 18:11:51 +00:00
Honghan Zhu 8f28b969e9 [Feat] DreamZero fix tp & cross attn cache (#4154) 2026-06-18 10:57:04 +00:00
zhumingjue138 2d2258890b [CI] skip ci for issue 4537 (#4538) 
Signed-off-by: zhumingjue <zhumingjue@huawei.com>
 2026-06-18 17:53:34 +08:00
Zening Chen 0383fde38a [Doc] Qwen3-TTS: add 0.6B on 1x RTX 4090 and fix broken links (#4026) 
Signed-off-by: Zening Chen <59945561+zeningc@users.noreply.github.com>
Signed-off-by: zeningc <zening.chen@yahoo.com>
 2026-06-18 17:31:36 +08:00
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
wangyu dff8cda844 [SKILLS] Add vllm-omni-test agent skill for CI-aligned test generation (#4434) 
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: [Your Name] <[Your Email]>
 2026-06-18 17:01:24 +08:00
Wallbreazzz c782746133 Add NPU support for OmniMRotaryEmbedding (#3609) 
Signed-off-by: Wallbreazzz <110282866+Wallbreazzz@users.noreply.github.com>
 2026-06-18 16:58:40 +08:00
Alicia db8bc2c71d Update VoxCPM and Qwen3TTS perf baseline. (#4521) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-06-18 16:56:13 +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
vraitiHongsheng LiuClaude Sonnet 4.5
 		77d395150b Remove unregister_vllm_metrics no-op patch (#4396) 
Signed-off-by: vraiti <vraiti@redhat.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-06-18 10:13:49 +08:00
汪志鹏 f195e44bc1 [BugFix]: Fix Bagel generate_image denoising schedule (#4509) 2026-06-18 02:02:38 +00:00
Yihong Jin 2f64c712fd [Quantization][Qwen3-Omni] Enable NVFP4 W4A4 serving on Blackwell (#4025) 
Signed-off-by: Yihong Jin <yihongjin404@gmail.com>
 2026-06-18 10:01:46 +08:00
Wallbreazzz 65bc737fd4 [DEBUG]Add has_preprocess branch to _dummy_run for models with preprocess stage (#4189) 
Signed-off-by: Wallbreazzz <110282866+Wallbreazzz@users.noreply.github.com>
 2026-06-18 07:56:19 +08:00
NumberWanandlishunyang12 d744940b18 Refactor: extract OmniStreamingVideoHandler base and QwenOmniStreamingVideoHandler (#4424) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Signed-off-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>
 2026-06-17 15:07:45 +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
blondeandClaude Opus 4.6 8fa0394d29 [Bugfix] Wire log_stats to AsyncOmni and add missing token metrics for non-text requests (#4482) 
Signed-off-by: blonde <164845202+blondeCS@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-06-17 21:31:44 +08:00
akshatvishu ed37d8e7a2 [Docs] Fix hallucinated stage CLI flags in documentation and comments (#4512) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-06-17 20:49:56 +08:00
akshatvishu d78a92ec54 [bugfix] Shim PreTrainedModel._tp_plan to fix MOSS-TTS-Nano load crash (#4398) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-06-17 17:17:03 +08:00
Honghan ZhuClaude Opus 4.8zhuhonghan
 		679cbe226a [Doc] Qwen image 2512 recipe (#4236) 
Signed-off-by: dph97 <nenbaying@163.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: zhuhonghan <z00806815@china.huawei.com>
 2026-06-17 17:04:58 +08:00
LHXuuuandHongsheng Liu dff757da9c [Perf][PrefixCache] Avoid per-step blocking write in OmniTensorPrefix… (#4106) 
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-17 16:53:47 +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
NATUREandAlicia 83e3b129f0 [Bugfix] Fix missing memory metrics info for bagel (ar->dit diffusion) (#4477) 
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-06-17 14:06:14 +08:00
Aliciaamy-why-3459herotai214bjf-frzdengyunyangHuang, ZeyuCHENrein yangNumberWan
 		1761253005 [CI] Update perf json baselines (#4289) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
Co-authored-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: dengyunyang <584797741@qq.com>
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: CHEN <116010019@link.cuhk.edu.cn>
Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: NumberWan <wantszkin2003@gmail.com>
 2026-06-17 14:02:50 +08:00
amy-why-3459 d897852258 [BugFix] Fix the issue of incorrect generated tokens (#4461) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-06-17 02:31:48 +00:00
Hyoseop SongZhou TaichangAlicia
 		b46c5af06f [Doc] Add guides for custom docker image build on NVIDIA CUDA [Skip-CI] (#1386) 
Signed-off-by: Hyoseop Song <crad_on25@naver.com>
Signed-off-by: Hyoseop Song  <crad_on25@naver.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
 2026-06-16 23:15:58 +08:00
Junhong LiulishunyangHongsheng LiuCopilot Autofix powered by AI
 		f200e988a6 [fix bug] add default limit for image generation (#3381) 
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: lishunyang <lishunyang12@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
 2026-06-16 22:54:26 +08:00
KristofferandHongsheng Liu e3621ec633 [Perf][qwen-image-edit] Skip attention-mask to avoid varlen path (#4293) 
Signed-off-by: kTorp <Kristoffer.Torp@amd.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-16 22:52:04 +08:00
Chendi.XueandHongsheng Liu e7f0db1067 [SDXL] SDXL model enabling (#4331) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-16 22:51:11 +08:00
Nick Cao 864d22164c [Bugfix] Fix DFlash prefix cache corruption due to missing lookahead block (#4449) 
Signed-off-by: Nick Cao <ncao@redhat.com>
 2026-06-16 22:48:01 +08:00
Samit 5f5b77aa9c [BugFix][Qwen-Image] align txt_seq_lens RoPE width with padded embeds (#4474) 
Signed-off-by: samithuang <285365963@qq.com>
 2026-06-16 19:09:25 +08:00
Weiming LiaoandCanlin Guo 3fa8817fc5 [BugFix][NPU]: Fix npu model runner too many values to unpack ($[1][0][4]) (#4454) 
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-06-16 19:06:51 +08:00
Zhou TaichangandClaude Opus 4.8 a62420450c [CI][Rebase]: run full e2e suite in rebase Ready/Merge pipelines in the rebase pipeline[skip-ci] (#4478) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-16 16:49:19 +08:00
TJian 5cce797c03 [Bugfix] [CI] [ROCm] [CUDA] Fix voxtral test (#4380) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-06-16 16:39:23 +08:00
akshatvishu d8a72be206 fix(models): remove invalid sampling_metadata parameter from logits_processor (#4456) 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
 2026-06-16 14:41:40 +08:00
Zheng WengangandHongsheng Liu ba4932c364 [Bugfix] Fix multi-replica stage identity and clean up redundant deploy config (#4410) 
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-06-16 14:08:11 +08:00
Yuekai ZhangandClaude Opus 4.8 dc14380796 [BugFix] higgs-audio-v3: load codec lazily under load_format=dummy (#4368) 
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-16 14:07:16 +08:00