anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
716 Commits 235 Branches 31 Tags
86e20769fd7016c4d61fa85d93b4a3cd0d91c185
Commit Graph
56 Commits
Author SHA1 Message Date
tzhouam 0099eebb3f Refactor OmniEngineArgs and AsyncOmniEngineArgs to improve compatibility with partial payloads by using getattr for various attributes. Update GPUGenerationModelRunner and OmniGPUModelRunner to replace the activate_lora parameter with num_active_loras for better clarity and backward compatibility. This change enhances the handling of LoRA activation during model runs. 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-12 03:33:50 +00:00
tzhouam 3663e803d1 rebase 2026/02/11 
vllm: 4a1550d22d7058e129d0e1257e726b3bf4a77025

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-11 02:43:49 +00:00
tzhouam 279b6b5050 Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-11 01:44:54 +00:00
dongbo910220andhsliuustc0106 43e8747c00 [Feat]: support VAE patch parallelism (#756) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: hsliuustc0106 <liuhongsheng4@huawei.com>
 2026-02-10 17:36:10 +08:00
tzhouam 58d09ed656 reabse 2026/02/10 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-10 03:36:09 +00:00
tzhouam 7e4a604d4d reabse 2025/2/9 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-09 03:07:43 +00:00
tzhouam 24b04f58a0 rebase 2026/2/5 2026-02-05 10:52:28 +00:00
Zhou Taichangand汪志鹏 70ef548448 Dev/rebase v0.15.0 (#1159) 
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-02-03 12:24:45 +08:00
tzhouam 6568a78a26 Remove unused tokenizer argument from OmniInputProcessor class docstring 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-02 03:12:43 +00:00
tzhouam 4b895459e4 Merge branch 'main' into dev/vllm-align 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-01-30 02:53:03 +00:00
amy-why-3459andRein Yang dd518973de [BugFix] Fix the accuracy issue of multimodal input. (#1020) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Rein Yang <ruiruyang2@gmail.com>
 2026-01-29 19:30:11 +08:00
Canlin Guo c9392dff01 [Hardware] Support platforms and plugin system (#774) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-01-28 22:12:52 +08:00
tzhouam 52d0122fb5 [Enhancement] Refactor OmniInputProcessor and related classes for improved prompt handling 
- Updated OmniInputProcessor to streamline input processing, including enhanced handling of prompt embeddings and additional information.
- Introduced OmniTextPrompt and OmniEmbedsInputs to support new input structures with optional metadata.
- Modified input preprocessing methods to accommodate new prompt types and ensure compatibility with multimodal inputs.
- Improved error handling and type checking for data parallel configurations.

Signed-off-by: [Your Name] <your.email@example.com>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-01-28 15:42:05 +08:00
tzhouam b26a9735e6 [Enhancement] Update type hint for stage_connector_spec in OmniEngineArgs and AsyncOmniEngineArgs 
- Changed type hint for stage_connector_spec from 'any' to 'Any' for improved type checking and consistency.
- Ensured compatibility with typing standards in the arg_utils module.

Signed-off-by: [Your Name] <your.email@example.com>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-01-28 15:41:20 +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
amy-why-3459Rein YangCHENHongsheng Liu
 		52bf1e2f40 [Feature]Support async computation and communication across stages by chunks (#727) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: CHEN <116010019@link.cuhk.edu.cn>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-01-26 11:21:24 +08:00
汪志鹏andwzliu 7f821be57b Support Bagel Model (#726) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: wzliu <wzliu@connect.hku.hk>
 2026-01-22 23:09:55 +13:00
Gao Han a54c323952 [Model] Support Qwen3-TTS model series (#895) 
Signed-off-by: Gaohan123 <hgaoaf@connect.ust.hk>
 2026-01-22 16:57:37 +08:00
+13
Zhou TaichangJaredforRealrootJustQJXU MingshiSihyeon JangJiangyun ZhucatcatZiming HuangYuhan LiuAliciaSamitYueqian LinWeiQing ChenPeiqi YinDidan DengHongsheng Liuwangyuwangyu31577汪志鹏John Liu BUAAD!NE$Hroot
 		776c3a794e Dev/rebase 0.14.0 (#847) 
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: root <root@hk01dgx039.cm.cluster>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: TangPeng <85704592@qq.com>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: iwzbi <wzbi@zju.edu.cn>
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
Signed-off-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: John Liu BUAA <liukecheng97@gmail.com>
Signed-off-by: Dinesh G <G.Dinesh@ibm.com>
Signed-off-by: gDINESH13 <dinesh13g@gmail.com>
Signed-off-by: root <root@hk01dgx028.cm.cluster>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: root <root@hk01dgx039.cm.cluster>
Co-authored-by: JustQJ <37905360+JustQJ@users.noreply.github.com>
Co-authored-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
Co-authored-by: Sihyeon Jang <uneedsihyeon@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: catcat <108673086+iwzbi@users.noreply.github.com>
Co-authored-by: Ziming Huang <hzm414167@alibaba-inc.com>
Co-authored-by: Yuhan Liu <30294295+liuyuhanalex@users.noreply.github.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: John Liu BUAA <liukecheng97@gmail.com>
Co-authored-by: D!NE$H <67671800+gDINESH13@users.noreply.github.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
 2026-01-21 00:25:25 +08:00
Chenguang ZhengyinpeiqiHongsheng Liu
 		595e7c0032 [Core] Supports stage abstraction in the diffusion model (#391) 
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-27 01:59:33 +13:00
wuhangandHongsheng Liu b3d212e985 [Perf] Optimise tensor concat perf in output processor (#467) 
Signed-off-by: wuhang <wuhang6@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-25 15:54:41 +00:00
dsinghvi b06a5148f6 bug resolution for omni models registration not present in vllm (#397) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
 2025-12-22 15:50:26 +08:00
Zhou TaichangRein YangIsotr0py
 		8939eb835d [Rebase] Rebase to vllm 0.12.0 (#335) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-12-19 16:42:02 +08:00
Cyrus Leung c091a03d82 [Chore] Bump Python version and apply formatting changes for v0.12 release (#126) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-16 15:19:40 +08:00
Baoyuan Qi cfe7ad47c1 Fix: Safe handling for multimodal_config to avoid 'NoneType' object h… (#227) 
Signed-off-by: Baoyuan Qi <qibaoyuan@126.com>
 2025-12-07 11:40:17 +08:00
Canlin GuoIsotr0pyGao Han
 		f75c21bcd0 [E2E] Add Qwen2.5-Omni model test with OmniRunner (#168) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Gao Han <gaohan19@huawei.com>
 2025-12-06 06:20:26 +00:00
R2-YandRein 0a4e5a8710 [Feature] add support for Qwen3-omni (#55) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: Rein <rein@Reins-MacBook-Air.local>
 2025-11-30 04:44:01 +08:00
Roger WangandGao Han a5800cd2c2 [Doc] Misc documentation polishing (#98) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Gao Han <gaohan19@huawei.com>
Co-authored-by: Gao Han <gaohan19@huawei.com>
 2025-11-29 20:42:39 +08:00
Gao Han db81ee9f69 [Docs] optimize and supplement docs system (#86) 
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
 2025-11-28 11:03:52 +08:00
Jiangyun Zhu 5707fc78d5 [CI] fix ci and format existing code (#71) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-11-18 20:54:26 +08:00
Gao Han c5a89302f1 [Feature] Support online inference (#64) 
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
 2025-11-17 14:44:10 +08:00
Gaohan123 6e1478222e Dependency refractored to vLLM v0.11.0 
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
 2025-11-04 22:06:41 +08:00
Gaohan123 6cf73c4e80 Remove unused files and fix some bugs 2025-10-25 18:02:11 +08:00
tzhouam 3b1324ea39 Merge branch 'main' into end2end_fixup 2025-10-24 17:41:03 +08:00
tzhouam 3265e857eb Refactor OmniLLM and MultimodalOutputProcessor initialization 
- Removed AsyncOmniLLM from the main entry points as it is not supported yet.
- Updated the constructor of MultimodalOutputProcessor to set a default value for engine_core_output_type.
- Adjusted output type handling in various methods to utilize the new default engine_core_output_type for consistency.
 2025-10-24 17:15:34 +08:00
Gaohan123 171f3c1ea7 fix conflicts 2025-10-24 16:49:19 +08:00
Gaohan123 a04e945166 add precommit 2025-10-24 16:20:58 +08:00
Zhou Taichang 582639c77a Merge branch 'main' into feat/hidden-state-input-request-input-processor-patch 
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
 2025-10-24 11:52:45 +08:00
tzhouam 63c72f4c2b Merge branch 'feat/hidden-state-input-request-input-processor-patch' of https://github.com/tzhouam/vllm-omni into feat/hidden-state-input-request-input-processor-patch 2025-10-24 11:40:49 +08:00
tzhouam a97409efef Add dtype mapping method in OmniProcessor 
- Introduced a static method `_dtype_to_name` to map PyTorch data types to their string representations.
- Updated the `dtype_str` assignments in the `OmniProcessor` class to utilize the new mapping method for improved readability and maintainability.
 2025-10-24 11:40:43 +08:00
tzhouam 4cd3b36fa0 Refactor OmniProcessor and update parsing logic 
- Removed redundant imports of `torch` and `numpy` in `OmniProcessor` class.
- Improved comments in `parse_singleton_prompt_omni` function for clarity on token handling.
- Ensured `current_platform` is imported only once for better code organization.
 2025-10-24 11:27:30 +08:00
Hongsheng Liu 4a4c3c1b82 Merge pull request #20 from tzhouam/feat/multimodal-output-processor 
[Engine]Refactor output processing for multimodal capabilities in vLLM-omni
 2025-10-24 11:25:23 +08:00
Zhou TaichangandCopilot d0423129f8 Apply suggestion from @Copilot 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
 2025-10-24 11:14:58 +08:00
Zhou TaichangandCopilot b04f114773 Apply suggestion from @Copilot 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
 2025-10-24 11:14:41 +08:00
tzhouam 6b196dee24 Enhance error handling in output processing for multimodal tensors 
- Added logging for exceptions during tensor movement to CPU in OmniRequestState and MultimodalOutputProcessor.
- Improved robustness by ensuring the output pipeline continues without crashing on errors.
- Updated comments for clarity on error handling behavior.
 2025-10-24 11:01:32 +08:00
tzhouam 3a27ff51d0 add back the diffusion engine as a placeholder for the actural diffusion engine in the future 2025-10-23 10:04:27 +08:00
Gaohan123 6111c288d0 fix some reviews from gemini 2025-10-22 17:46:10 +08:00
tzhouam 83e7f6ba12 Add Omni model components and input processing for hidden states support 
- Introduced `OmniModelRunnerOutput` and `OmniRequestOutput` classes for handling multimodal outputs.
- Implemented `OmniEngineCoreRequest` and `OmniInputPreprocessor` to manage prompt embeddings and additional information.
- Created `OmniTokensPrompt`, `OmniTokenInputs`, and `OmniEmbedsPrompt` for enhanced token handling.
- Added parsing and preprocessing functions to support new input structures.
- Removed the obsolete `diffusion_engine.py` file as part of the refactor.
 2025-10-22 15:16:25 +08:00
Gaohan123 20cfd15cc6 Add entrypoint class and stage management 2025-10-22 14:37:55 +08:00
tzhouam b4fa09f756 Refactor output processing for multimodal capabilities in vLLM-omni 
- Introduced OmniRequestState to manage multimodal request states.
- Enhanced MultimodalOutputProcessor to handle various output types including images, text, and latents.
- Implemented methods for accumulating multimodal tensors and processing outputs.
- Updated output handling to ensure compatibility with vLLM's base processor while allowing custom modality handlers.
 2025-10-22 11:54:07 +08:00