anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,829 Commits 235 Branches 31 Tags
69fd466fba56b9dcdcd1e76d9b7986ebf37fb3fa
Commit Graph
77 Commits
Author SHA1 Message Date
Gao Han 69fd466fba Merge branch 'main' into feat/diffusion-prefetch-protection 2026-06-02 23:22:08 +08:00
NumberWan 35ee3c7543 [BugFix]Qwen-Image performance regression by using torch RMSNorm(RMSNorm backend) (#4074) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-06-02 23:19:17 +08:00
tzhouam 617c6ca55f feat: enhance model loading with prefetching and retry logic 
- Introduced `from_pretrained_with_prefetch` to handle racy cache scenarios by re-prefetching and retrying on failures.
- Updated various model pipelines to utilize the new prefetching mechanism, ensuring robust loading of model components.
- Prefetch logic added to multiple models, including HunyuanVideo, LongCatImage, and QwenImage, to mitigate issues with incomplete cache states.
 2026-06-02 09:01:47 +00:00
+1
Zhou TaichangClaude Opus 4.7skfZheng WengangHongsheng LiuWeiQing ChenSYLARYueqian Linnainiu258JasonYueqian Lin
 		f92d84fcf9 [Rebase] Rebase to vllm releases/v0.22.0 (#3891) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: nainiu258 <cperfect02@163.com>
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com>
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-06-01 11:08:12 +08:00
NumberWan 6f4bd3e45c [BugFix]Qwen-Image performance regression by using omni RMSNorm(RMSNorm backend) (#3933) 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
 2026-05-31 08:06:18 +08:00
rongfu.lengandPeter Pan c349f62839 [Feat] opt qwen image model load use ColumnParallelLinear replace ReplicatedLinear (#3875) 
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Peter Pan <Peter.Pan@daocloud.io>
 2026-05-27 09:02:17 +00:00
baonudesifeizhai 076c34abfb （Phase 2）Add ModelOpt mixed FP8/NVFP4 support for image generation (#3570) 
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
 2026-05-22 10:39:10 +08:00
LuandSYLAR 14e5baceaf [Qwen-Image] Drop unused vision tower from text encoder (#3608) 
Signed-off-by: lulugoodcoder <luludachiever@gmail.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-05-19 19:19:58 +08:00
Ayush AgarwalandHongsheng Liu b968373c88 enhancement: extend to dmd2 to image generation + add flux, qwen image pipelines (#2974) 
Signed-off-by: ayushag <ayushag@nvidia.com>
Signed-off-by: Ayush Agarwal <ayushag@nvidia.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-05-08 21:37:57 +08:00
Ting FUasukaqaq-sjaderHongsheng LiuGao Han
 		e49fbd8a2d [Feat] DiffusionEngine Support async batch infer (#2729) 
Signed-off-by: Semmer <semmer@live.cn>
Signed-off-by: jader <yjader@foxmail.com>
Signed-off-by: asukaqaq-s <1311722138@qq.com>
Co-authored-by: asukaqaq-s <1311722138@qq.com>
Co-authored-by: jader <yjader@foxmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-05-06 09:47:13 +12:00
Zhou TaichangandYuanheng Zhao 7f2b1e9386 [Rebase] Rebase to vllm 0.20.0 (#3232) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com>
 2026-04-30 09:56:59 +12:00
WeiQing ChenandGao Han f658bcb0bf [Bugfix] Limit Qwen-Image-Edit-2511 input image count (#2840) 
Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-04-17 20:07:30 +08:00
WeiQing Chen 3079e943de [Bugfix] enforce max_sequence_length for Qwen-Image and Wan2.2 series before encoding (#2847) 
Signed-off-by: david6666666 <530634352@qq.com>
 2026-04-17 10:40:36 +08:00
Zhang Jianandpjh4993 c6d76d081b [Bugfix] Fix broken fp8 quantisation on Z-Image-Turbo, Qwen-Image, FLUX.1-dev (#2795) 
Signed-off-by: Zhang <jianmusings@gmail.com>
Co-authored-by: pjh4993 <pjh4993@naver.com>
 2026-04-15 14:25:41 +00:00
fan2956andCanlin Guo 2dff2d7c74 [PERF] Wan2.2 support adalayernorm fused op (#2585) 
Signed-off-by: fan2956 <zhoufan53@huawei.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-04-15 14:02:41 +08:00
WeiQing Chen 85d63c47f9 [Bugfix] Fix Qwen-Image min-size normalization for tiny requests (#2637) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-04-09 20:51:01 +08:00
LancerandDidan Deng 328de586aa [Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-04-06 11:49:35 +08:00
Lancer 70a62651b9 [Feat] support HSDP for Qwen-image series, Z-Image, GLM-Image (#2029) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-04-01 20:01:09 +08:00
SYLAR 6b93459826 [Core] Unified quantization framework (#1764) 2026-03-24 18:56:55 +08:00
WeiQing Chen d6b55b9196 [Quantization] feat: add qwen-image gguf adapter (#1755) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-03-23 13:24:54 +00:00
Wu JIAZHEN da7a8f8014 reafator pipeline stage/step pipeline (#1368) 
Signed-off-by: asukaqaq-s <1311722138@qq.com>
 2026-03-20 19:21:50 +08:00
SamitandHongsheng Liu 5699fe7a96 [Bugfix] Fix config misalignment between offline and online diffusion inference (Wan2.2, Qwen-Image series) (#1979) 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-03-19 16:00:26 +08:00
dengyunyangbjf-frzDidan Deng
 		fde4808723 [Performance] diffusion timing (#1757) 
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-03-19 12:26:12 +08:00
Canlin Guo d5ddc190f9 [UX] Add progress bar for diffusion models (#1652) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-03-05 23:56:14 +08:00
dongbo910220Hongsheng LiuJiangyun Zhu
 		675c35db97 [Refactor] lora: reuse load_weights packed mapping (#991) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2026-03-04 02:58:43 +00:00
dengyunyang d275c0c993 [FEATURE] Tile/Patch parallelism refactor for easily support other models (#1366) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2026-03-03 15:48:51 +08:00
SYLAR 830d261f9d [Feature]: FP8 Quantization Support for DiT (#1034) 
Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
 2026-02-11 21:01:35 +08:00
SYLARandHongsheng Liu 8a9644c821 [Bugfix] Fix image edit RoPE crash when explicit height/width are provided (#1265) 
Signed-off-by: lishunyang <lishunyang12@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-02-10 21:18:36 +00:00
Zeyu Huang | 黃澤宇andHongsheng Liu 7672298075 bugfix: /images/edits endpoint fails pipeline data format check (#1141) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-02-04 09:36:57 +08:00
Jiangyun Zhu 4d8e29075a [Bugfix] fix qwen image oom (#1168) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-02-03 18:13:00 +08:00
Canlin Guo 3bc3c95708 [Bugfix][Qwen-Image-Edit] Add a warning log for none negative_prompt (#1170) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-02-03 18:12:11 +08:00
Didan DengandHongsheng Liu 23cf48d7bb [Perf]: CFG parallel abstraction (#851) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-30 16:23:44 +00:00
XU MingshiandHongsheng Liu be835c4483 [BugFix] Fix modulate_index shape error in Qwen-Image-Edit Task (#1100) 
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-30 13:44:58 +00:00
Yuanheng ZhaoHongsheng LiuCopilot
 		2923d5a91e [Feature] Support DiT Layerwise (Blockwise) CPU Offloading (#858) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-01-30 17:35:09 +08:00
Canlin Guo 0c8b5ac2d5 [Bugfix] Set VaeImageProcessor do_convert_rgb True (#1032) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-01-29 12:02:39 +00:00
Jiangyun Zhu 43c6f520ca [Bugfix] fix qwen image layerd in dummy run (#1027) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-29 15:18:19 +08:00
Zeyu Huang | 黃澤宇 d64bbde561 [Frontend][Model] Support batch request with refined OmniDiffusionReq… (#797) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
 2026-01-28 16:07:42 +08:00
Jiangyun Zhu 4a3a1b6de8 [Perf] avoid cpu op in QwenImageCrossAttention (#942) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-27 12:15:35 +08:00
Andy Zhoudongbo910220Samit
 		5037af1033 [Feature] Diffusion LoRA Adapter Support (PEFT compatible) for vLLM alignment (#758) 
Signed-off-by: AndyZhou952 <jzhoubc@connect.ust.hk>
Signed-off-by: Andy Zhou <jzhoubc@connect.ust.hk>
Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: Andy Zhou <46011930+AndyZhou952@users.noreply.github.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Samit <285365963@qq.com>
 2026-01-27 10:22:40 +08:00
SamitandHongsheng Liu 978a290d6e [Bugfix] Fix diffusion pipeline CFG (guidance_scale parsing failure bug) (#922) 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-26 05:09:03 +00:00
Jiangyun Zhu 58efc5dde3 [Misc] fix qwen image family redundant computation (#868) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-21 09:58:08 +00:00
XU Mingshi 25b08b3371 [Diffusion] Non-Intrusive Sequence Parallelism (SP) Model Support Abstraction for vLLM-Omni Framework (#779) 
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
 2026-01-21 14:43:09 +08:00
Jiangyun Zhu 3fc4f988ea [diffusion] add tp support for qwen-image and refactor some tests (#830) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-19 14:20:31 +08:00
Didan Deng 43ec7f701b [Feature] Flash Attention to Support Attention Mask (#760) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-01-16 11:01:11 +08:00
Samit 2d5faf3634 [Bugfix] Fix generation artifacts of Qwen-Image-Edit-2511 and update pipeline DiT param parsing (#776) 
Signed-off-by: samithuang <285365963@qq.com>
 2026-01-15 11:18:28 +08:00
Jiangyun Zhu c784b3e07d [core] add torch compile for diffusion (#684) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2026-01-09 04:05:44 +13:00
Didan Deng 4df794bdaa [Bugfix] Solve Ulysses-SP sequence length not divisible by SP degree (using padding and attention mask) (#672) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-01-08 00:02:22 +08:00
ApsarasX 89f47c910a [Bugfix] Fix f-string formatting in image generation pipelines (#689) 
Signed-off-by: ApsarasX <apsarax@outlook.com>
 2026-01-07 14:12:58 +00:00
Didan Deng 14c04d0fd4 [Diffusion][Feature] CFG parallel support for Qwen-Image (#444) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-01-06 17:34:50 +08:00
catcatandHongsheng Liu 026f613e57 [Misc] Merge diffusion forward context (#582) 
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-05 22:49:03 +08:00