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
450 Commits
Author SHA1 Message Date
tzhouam 86e20769fd Add SSL context support in benchmark function for improved connection handling 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-12 08:52:27 +00:00
tzhouam 3e89c99001 Merge remote-tracking branch 'remotes/origin/main' into dev/vllm-align 2026-02-12 07:16:25 +00:00
tzhouam c751f0d684 Update Dockerfile.ci to install a new version of vllm from a different extra index URL. Refactor import statement in serving_chat.py to use the correct BaseRenderer module path. 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-12 06:37:17 +00:00
SamitandFlora Feng 9c00852d85 [Feature] Support Wan2.2 T2V and I2V Online Serving with OpenAI /v1/videos API (#1073) 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Signed-off-by: SamitHuang <285365963@qq.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
 2026-02-12 14:28:32 +08:00
Ziming HuangHongsheng LiuCopilot
 		0b56fba7b3 [Pref] Support Qwen3 Omni code2wav batch infernce with async chunk (#1246) 
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: Ziming Huang <1520787127@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-02-12 11:50:10 +08:00
tzhouamandCursor 50f2b1e854 Merge origin/main into dev/vllm-align 
Co-authored-by: Cursor <cursoragent@cursor.com>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-12 03:41:38 +00:00
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
Junhong Liu 82fd2c3637 Fix yield token metrics and opt metrics record stats (#1292) 2026-02-12 00:52:05 +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
Yueqian Lin 5fb7d137c7 [Bugfix][Qwen3-TTS] Preserve original model ID in omni_snapshot_download (#1318) 2026-02-11 18:24:45 +08:00
Ekagra Ranjan dd302b63c4 [Bugfix][Qwen3-TTS] Fix task type (#1317) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
 2026-02-11 15:49:15 +08:00
Zhou Taichang a854f0b7ff [Debug] Add trigger to concurrent stage init (#1274) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-11 14:18:18 +08:00
tzhouam 3663e803d1 rebase 2026/02/11 
vllm: 4a1550d22d7058e129d0e1257e726b3bf4a77025

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-11 02:43:49 +00:00
rein yang 963b64e7ae [Bugfix] fix precision issues of qwen3-omni when enable async_chunk without system prompt (#1288) 
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
 2026-02-11 10:03:41 +08:00
tzhouam 279b6b5050 Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-11 01:44:54 +00:00
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
汪志鹏 8228b5a8fe [Bagel]: Support TP (#1293) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2026-02-11 00:17:44 +13:00
Canlin Guo e192b0a6c5 [Misc] Add per-request generator_device to online image gen and edit (#1183) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-02-10 18:47:08 +08:00
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
Yueqian Lin f55ce9c793 [Test] Add e2e tests for Qwen3-TTS speech endpoint (#1206) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-02-10 16:33:39 +08:00
amy-why-3459 ee624d0686 [BugFix] Fixed the issue where ignore_eos was not working. (#1286) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-02-10 16:08:20 +08:00
zhou zhuoxinandCopilot 109bb97b2c [Fix]Ensure HuggingFace downloads complete before initialization. (#1213) 
Signed-off-by: zhou zhuoxin <zhouzhuoxin1508@outlook.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-02-10 16:05:12 +08:00
Yan Ma 9327cccde6 [Bugfix] Fix 'NoneType' AttributeError in stable-diffusion model detect (#1254) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
 2026-02-10 15:25:08 +08:00
JohnJan f73fa1fbe7 [feature]: support Flux.1-dev CFG-Parallel (#1269) 2026-02-10 14:54:35 +08:00
tzhouam c3d35ed5fe pass local t2i test 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-10 06:20:26 +00:00
tzhouam 58d09ed656 reabse 2026/02/10 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-10 03:36:09 +00:00
tzhouam 064595a97c Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-10 02:22:49 +00:00
tzhouam e0f540fe98 Enhance Dockerfile.ci to synchronize flashinfer runtime package versions with installed flashinfer-python, ensuring compatibility across components. Additionally, improve error handling in ring_globals.py for flashinfer import failures, logging warnings for fallback scenarios. 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-10 02:17:00 +00:00
Jiaping Wu 5fea4823b7 [Model] SupportHunyuanImage3 Diffusion Model in vllm-omni (#1085) 
Signed-off-by: Semmer2 <semmer@live.cn>
 2026-02-10 03:03:44 +13:00
Junhong LiuandHongsheng Liu 9af6fb9a1f [Feature] Opt metrics structure (#891) 
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Signed-off-by: Junhong Liu <ljh_lbj@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-02-09 19:17:32 +08:00
XU Mingshi ac397ae2a0 [Diffusion][Perf] Remove Redundant Communication Cost by Refining SP Hook Design (#1275) 
Signed-off-by: mxuax <mxuax@connect.ust.hk>
Signed-off-by: XU Mingshi <91017482+mxuax@users.noreply.github.com>
 2026-02-09 19:10:10 +08:00
Chenguang Zheng c6b526bc2e fix: add diffusion offload args to OmniConfig group instead of serve_parser (#1271) 
Signed-off-by: Chenguang ZHENG <645327136@qq.com>
 2026-02-09 11:46:00 +08:00
tzhouam 7e4a604d4d reabse 2025/2/9 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-09 03:07:43 +00:00
tzhouamandCursor 03c6a58f69 Merge origin/main into dev/vllm-align; resolve omni_stage.py conflicts 
Co-authored-by: Cursor <cursoragent@cursor.com>

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-09 01:52:31 +00:00
dsinghvi 59024bee62 Process-Scoped GPU Memory Accounting (#1204) 
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
 2026-02-08 22:43:02 +08:00
Yueqian Lin accf334112 [bugfix] Fix multimodal_output property to check completion outputs where audio data is attached (#1203) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-02-08 00:39:09 +08:00
Yueqian Lin 53a44c56fe [Bugfix] Fix padding bug in 12Hz tokenizer ConvTranspose1d decode (#1241) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
 2026-02-08 00:35:49 +08:00
ApsarasX 87847a214a [Bugfix] Ensure seed=0 is correctly handled in image edit (#1248) 
Signed-off-by: ApsarasX <apsarax@outlook.com>
 2026-02-07 07:09:54 +08:00
ApsarasX 10f841bb98 [Bugfix] Fix '--max-generated-image-size' cli args type (#1249) 
Signed-off-by: ApsarasX <apsarax@outlook.com>
 2026-02-06 21:44:51 +08:00
XU MingshiandHongsheng Liu 11a5a914ca [Bugfix] Fix wan2.2 ti2v (#1221) 
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>
 2026-02-06 17:28:49 +08:00
tzhouam 7f54fd2f54 Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-06 02:26:06 +00:00
Canlin Guo 285d71b26a [Refactor] Reuse upstream Qwen3MoeSparseMoeBlock (#1202) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2026-02-06 01:06:50 +00:00
tzhouam 41e22e2770 [Refactor] Clean up code by removing unnecessary lines and adding missing imports in async_omni_llm.py, omni_stage.py, omni.py, and api_server.py 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-05 11:02:03 +00:00
tzhouam 24b04f58a0 rebase 2026/2/5 2026-02-05 10:52:28 +00:00
weichen c4933ec2aa [Wan 2.2][Diffusion] Add TP Support (#964) 
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2026-02-05 18:11:12 +08:00
tzhouam 0144a424ed Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-05 01:44:34 +00:00
JohnJanandJiangyun Zhu 8135ee81e6 [feature]: support flux cache_dit (#1145) 
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2026-02-04 22:10:04 +08:00
amy-why-3459 d1cf4c4c0f [Bugfix] async_chunk rebase v0.15.0 (#1195) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-02-04 20:50:09 +08:00
Zhou Taichang f1960d8dfd [Feature] Enable use_audio_in_video for Qwen 3 Omni Online (#1198) 
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
 2026-02-04 20:48:25 +08:00
WeiQing Chen 38ec7eda90 [Bugfix] Fix tp+sp accuracy, incorrect process group mapping (#1178) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-02-04 16:54:47 +08:00