anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,775 Commits 235 Branches 31 Tags
c69ed4037dcbae7306cba9094cb42bf94de464f0
Commit Graph
1775 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
tukwilaandHongsheng Liu 8ddf052a95 upload collect_env.py (#429) 
Signed-off-by: guangli.bao <guangli.bao@daocloud.io>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-26 14:11:35 +08:00
Canlin GuoandHongsheng Liu fe3d9a6a81 [NPU][Upgrade] Upgrade to v0.12.0 (#447) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-26 14:10:23 +08:00
Junhong Liu 51eefbfebc [BugFix] initial sampling_params_list when offline inference (#468) 
Signed-off-by: Junhong <liujunhong11@huawei.com>
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Signed-off-by: Junhong Liu <ljh_lbj@163.com>
 2025-12-26 13:54:12 +08:00
Canlin Guo 4f1c34099a [Refactor][Diffusion] Make NPUWorker inherit GPUWorker (#483) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-12-26 12:54:03 +08:00
dengyunyangandHongsheng Liu a500ca1f28 [Feature] logger refactor (#466) 
Signed-off-by: dengyunyang <584797741@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-26 08:42:06 +08:00
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
WeiQing ChenandHongsheng Liu beb474b65c [Benchmark] DiT models Performance benchmark(T2I/I2I/T2V/TI2V) (#362) 
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-26 04:50:47 +13:00
Canlin Guo e1f9691120 [Clean] Remove the redundant decoding payloads logic (#404) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-12-26 04:48:34 +13:00
knlnguyen1802andJiangyun Zhu 15523a3909 RPC support for OmniDiffusion (#371) 
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2025-12-25 22:26:30 +08:00
Ziming Huang 1a7dcdf65c [Feature] Support Qwen Omni online batch inference (#438) 
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
 2025-12-25 19:38:48 +08:00
Yueqian LinandHongsheng Liu 3ec35e5409 [Model] Add Wan2.2 I2V and TI2V pipeline support (#329) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-25 16:45:13 +08:00
catcatandiwzbi d51f4c086d [BugFix] Use weakref.finalize to cleanup DiffusionEngine (#461) 
Signed-off-by: iwzbi <iwzbi@zju.edu.cn>
Co-authored-by: iwzbi <iwzbi@zju.edu.cn>
 2025-12-25 11:32:42 +08:00
Peiqi Yin e9e6b3711c [Core] customize process between stages, remove the need of "request_ids" in model forward, rebase to 0.12.0 (#458) 
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
 2025-12-24 13:26:33 +00:00
Wonjae Leeandwonjae.lee0 341457a121 [Feature] Support standard OpenAI API sampling parameters for thinker stage. (max_tokens...) (#450) 
Signed-off-by: wonjae.lee0 <wonjae.lee0@navercorp.com>
Co-authored-by: wonjae.lee0 <wonjae.lee0@navercorp.com>
 2025-12-24 20:39:01 +08:00
Peiqi Yin da7f25e14b [BugFix] Qwen3-Omni / Qwen2.5-Omni thinker batching with audio input (#451) 
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
 2025-12-24 18:43:00 +08:00
Wonjae Leeandwonjae.lee0 cbaf508665 [Docs] Add API usage examples for modality control in online serving (#411) 
Signed-off-by: wonjae.lee0 <wonjae.lee0@navercorp.com>
Co-authored-by: wonjae.lee0 <wonjae.lee0@navercorp.com>
 2025-12-24 15:57:32 +08:00
Alicia cfc356f01d [Docs] Update installation method. (#448) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
 2025-12-24 17:51:19 +13:00
rein yang c78c326eb3 [Docs] fix doc image loading error (#446) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
 2025-12-24 04:08:29 +00:00
rein yangandroot 2a3c50147a [Docs] how to add a new multi stage model document (#417) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Signed-off-by: root <root@hk01dgx028.cm.cluster>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
 2025-12-24 15:06:29 +13:00
Samit 2d42bdcc40 [Misc] Add Qwen-Image-Edit-2511 running script (#440) 
Signed-off-by: samithuang <285365963@qq.com>
 2025-12-24 04:26:16 +13:00
Canlin Guo 259fe1150c [Docs] Pin the installation on NPU as v0.11.0rc1 (#434) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-12-23 20:20:12 +08:00
Yuanheng Zhao edbd610060 [RFC] Clean and refactor TeaCache registry (#416) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2025-12-23 18:21:23 +08:00
Zeyu Huang a16476bebf [Doc] fix diagrams in Architecture Overview page (#430) 
Signed-off-by: Zeyu Huang <11222265+fhfuih@users.noreply.github.com>
 2025-12-23 18:20:43 +08:00
WeiQing Chen d9faeb29c0 [Doc] update diffusion_acceleration.md & FAQ memory troubleshooting (#406) 
Signed-off-by: David Chen <530634352@qq.com>
 2025-12-23 15:09:25 +08:00
Doug Smith 74c142460d DALL-E compatible image generation endpoint (#292) 
Signed-off-by: dougbtv <dosmith@redhat.com>
 2025-12-23 09:05:37 +08:00
Peiqi Yin 0e878a92d2 [BugFix] raise error when request.stream=True. (#350) 
Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
 2025-12-23 08:52:18 +08:00
elijahandhuangxulong ef827022b8 [Model] Add LongCat-Image-Edit support (#392) 
Signed-off-by: huangxulong <huangxulong@oschina.cn>
Signed-off-by: elijah <f1renze.142857@gmail.com>
Co-authored-by: huangxulong <huangxulong@oschina.cn>
 2025-12-22 21:31:50 +08:00
Alicia f363108425 [Doc] Refine the document. (#403) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
 2025-12-22 21:29:40 +08:00
Alicia 89e0836f78 [CI] Skip build wheel CI test for specific type files. (#401) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
 2025-12-22 19:17:37 +08:00
Didan DengandJiangyun Zhu ee2b78e826 [Diffusion][Bug-Fix]: Fix Ulysses SP Accurary Error (#377) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2025-12-22 17:48:39 +08:00
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
Alicia 36a20de5af Bump version to 0.12.0rc1 (#399) 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
 2025-12-22 15:00:13 +08:00
dsinghvi 92c20afdc1 [Feature]: Adding traceback for error in background worker (#385) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
 2025-12-22 13:21:53 +13:00
Canlin Guo 97a5860681 [Security][Feature] Use Msgpack in OmniSerializer instead of pickle (#310) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-12-22 13:21:16 +13:00
Jiangyun Zhu a7fe4fba4e [refactor] teacache refactor (#395) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-12-22 06:49:04 +08:00
TJian 01f28217b1 [Doc] fix wrong file name in Qwen-Image-Layered demo script (#396) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-12-22 06:48:45 +08:00
Yuanheng Zhao 6b9944f11d [Bugfix] Enable teacahce in QwenImageEditPlusPipeline (#379) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2025-12-21 15:58:15 +08:00
TJianandHongxia Yang 13584fd98e [ROCm] [CI] Add ROCm Dockerfile and AMD CI (vllm v0.12.0) (#280) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
 2025-12-21 11:51:37 +08:00
dengyunyang 85bc8bfa6a [New model] Support model qwen image layered (#381) 
Signed-off-by: dengyunyang <584797741@qq.com>
 2025-12-20 14:51:50 +00:00
Samit 96e4690013 [Bugfix] Fix image size logging bug for multiple image input (#384) 
Signed-off-by: samithuang <285365963@qq.com>
 2025-12-20 06:49:57 +08:00
dsinghviandHongsheng Liu 4586efe651 [Model] Ovis Image Model Addition (#263) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-19 20:05:34 +08:00
Jiangyun Zhu 6ec427f82f [Revert] revert diffusion warmup (#382) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-12-19 19:48:41 +08:00
rein yang c591ea124f [Bugfix] fix GPU VRAM calculation problem (#328) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
 2025-12-19 19:21:33 +08:00
Samit 094de95548 [Misc] Update qwen-omni gradio demo to use api server (#378) 
Signed-off-by: samithuang <285365963@qq.com>
 2025-12-19 18:09:43 +08:00
WeiQing Chen 628c0a9217 [Entrypoints] Support Qwen-Image-Edit 2509 online serving & update doc (#368) 
Signed-off-by: David Chen <530634352@qq.com>
 2025-12-19 16:50:32 +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
WeiQing Chen 9464e1479d [Entrypoints] online serving support usp args (#366) 
Signed-off-by: David Chen <530634352@qq.com>
 2025-12-19 11:59:07 +08:00
Jiangyun Zhu 5216cf4ae6 [Perf] torch compile for dit and rope kernel (#317) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-12-19 03:16:20 +00:00
AliciaandHongsheng Liu d6310e2ea9 [Doc] Rewrite checklist & update docs. (#360) 
Signed-off-by: Alicia Wang <115451386+congw729@users.noreply.github.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2025-12-19 06:11:54 +08:00
elijahandhuangxulong b5e50d552a [Model] Add LongCat-Image support (#291) 
Signed-off-by: elijah <f1renze.142857@gmail.com>
Signed-off-by: huangxulong <huangxulong@oschina.cn>
Co-authored-by: huangxulong <huangxulong@oschina.cn>
 2025-12-18 15:35:27 +00:00