Commit Graph
177 Commits
Author SHA1 Message Date
tzhouam f24273dc03 Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-13 09:50:11 +00:00
tzhouam 31e9fdbb57 Refactor chat_utils to remove unused multi-modal classes and add async audio extraction from video. Update README to reflect new entry point for audio extraction. Enhance serving_chat to process audio from video URLs when specified.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-13 03:27:16 +00:00
tzhouam 7e9cae56fc Refactor Dockerfile.ci to use precompiled VLLM installation and remove unused parse.py file. Update serving_chat.py to streamline rendering logic and enhance compatibility with new API. Modify OmniInputPreprocessor to directly handle SingletonDictPrompt, improving input processing efficiency.
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-13 02:28:25 +00:00
Taichang Zhou a6d633c319 debug
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
2026-02-12 23:46:20 +08:00
tzhouam 59a7602d6e debug
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-12 13:55:08 +00:00
Taichang Zhou 85a7b558ab rebase to v0.16.0
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
2026-02-12 21:30:54 +08:00
Taichang ZhouandCursor e2ced80d59 Merge origin/main into dev/rebase-v0.16.0.
Resolve arg_utils merge conflict and align CI base image tag to v0.16.0 for the vLLM rebase track.

Co-authored-by: Cursor <cursoragent@cursor.com>

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
2026-02-12 21:18:03 +08:00
dsinghviand汪志鹏 c6f314df4f [Feature]: Diffusion sleep to use process level memory calculation (#1276)
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
2026-02-12 12:17:54 +00:00
knlnguyen1802 9994594782 [Misc] Support WorkerWrapperBase and CustomPipeline for Diffusion Worker (#764)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
2026-02-12 19:23:51 +08:00
tzhouam f8959bcc6e Temp fix for metrics error in test_qwen3_tts
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-12 10:02:19 +00:00
Yuanheng ZhaoandSamit 8bf849c399 Refactor CPU Offloading Backend Pattern (#1223)
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
2026-02-12 17:29:55 +08:00
ab1acb27ff [Feature]async scheduling to overlap chunk IO and compute (#951)
Signed-off-by: CHEN <116010019@link.cuhk.edu.cn>
Co-authored-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
Co-authored-by: Gao Han <gaohan19@huawei.com>
2026-02-12 16:05:02 +08:00
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
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
Junhong Liu 82fd2c3637 Fix yield token metrics and opt metrics record stats (#1292) 2026-02-12 00:52:05 +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
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
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
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
tzhouam 064595a97c Merge remote-tracking branch 'origin/main' into dev/vllm-align 2026-02-10 02:22:49 +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
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
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
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
Junhong LiuandHongsheng Liu 959b3ca8c8 [Bugfix] E2E metric incorrect qwen3-omni with async chunk feature (#1018)
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>
2026-02-04 15:27:30 +08:00
Zhou Taichang d6f93b0f37 [Debug] Correct Unreasonable Long Timeout (#1175)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
2026-02-03 08:49:51 +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
ceanna93andanna df3b347cd9 [Misc] Align error handling with upstream vLLM v0.14.0 (#1122)
Signed-off-by: anna <lee.anna@navercorp.com>
Co-authored-by: anna <lee.anna@navercorp.com>
2026-02-01 21:59:08 +08:00
dengyunyang 70a5de9dd4 [FEATURE] /v1/images/edit interface (#1101)
Signed-off-by: dengyunyang <584797741@qq.com>
2026-01-31 14:13:36 +08:00
2e6895ff0e [Bugfix][Qwen3TTS] Load speaker_id/voices from model configuration (#1079)
Signed-off-by: pablo <juanz9312@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
2026-01-31 10:42:09 +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
Jiangyun ZhuandHongsheng Liu 8ad39570b8 [Bugfix] fix request_id of image generation in api server (#1112)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-01-31 00:05:34 +08:00
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
Pierre LE GUEN 2c294a750b fix: UnboundLocalError for role in streaming audio/image responses (#784)
Signed-off-by: Pierre Le Guen <26087574+PierreLeGuen@users.noreply.github.com>
2026-01-30 16:27:04 +08:00
7bfd3c069d [Benchmark] Add vLLM-Omni Omni model online benchmark (#780)
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-01-30 11:41:09 +08:00
dengyunyang 47a0969976 [Bugfix] pr conflict fix, bugfix ignore mm data from stages to async omni (#1025)
Signed-off-by: dengyunyang <584797741@qq.com>
2026-01-29 17:09:34 +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
Yueqian Lin cac6504adf [bugfix] remove vllm speech route (#1060)
Signed-off-by: linyueqian <linyueqian@outlook.com>
2026-01-29 16:02:59 +08:00