anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
1,090 Commits 235 Branches 31 Tags
a72a91b43e5e0e3f87d73d08e663c0e603f8dcd2
Commit Graph
1090 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
khluuandClaude Opus 4.6 a72a91b43e Simplify generate-nightly-index.py and install uv in pipeline 
Remove variant/ROCm/alias handling -- just generate a flat PEP 503
index. Install uv with Python 3.12 for faster wheel builds.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 15:26:14 -07:00
khluuandClaude Opus 4.6 9c66d3671e Restrict nightly index upload to main branch with NIGHTLY=1 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 15:15:22 -07:00
khluuandClaude Opus 4.6 462add601f Temporarily allow nightly index upload from any branch for testing 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 14:53:28 -07:00
khluuandClaude Opus 4.6 ca3e9e8568 Fix nightly pipeline: install uv with python 3.12, resilient s3 ls 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 14:40:25 -07:00
khluu 29523184fc p 
Signed-off-by: khluu <khluu000@gmail.com>
 2026-03-30 14:26:16 -07:00
Yangshen DengandClaude Opus 4.6 837679dbaa [Diffusion] Refactor CFG parallel for extensibility and performance (#2063) 
Signed-off-by: Yangshen Deng <yangshen.d@outlook.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-30 16:48:58 +00:00
Zeyu Huang | 黃澤宇andCopilot 0cf99144d6 [skip ci][Docs] reorganize multiple L4 test guidelines (#2119) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2026-03-31 00:12:14 +08:00
WeiQing Chen 1ca942999a [Bugfix] fix: validate layered image layers range (#2334) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-03-30 21:27:09 +08:00
WeiQing Chen 1eee8435e1 [Bugfix] fix: return 400 for unsupported multi-image edits such as Qwen-Image-Layered (#2298) 
Signed-off-by: David Chen <530634352@qq.com>
 2026-03-30 20:24:57 +08:00
Didan Deng 911be0d426 [skip ci][Doc] Refine the Diffusion Features User Guide (#1928) 
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-03-30 14:28:04 +08:00
wangyuyenuo26R2-YYueqian Lin
 		c9370f493e [Test] Add Qwen-tts test cases and unify the style of existing test cases (#2195) 
Signed-off-by: yenuo26 <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: yenuo26 <410167048@example.com>
Co-authored-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-03-30 01:02:28 -04:00
Lancer 32af3af262 [Bugfix] Fix Qwen3TTSConfig init order to be compatible with newer Tansformers(5.x) (#2306) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-03-30 09:50:16 +08:00
chickeyton fa0792a0aa [Doc] Add transformers version requirement in GLM-Image example doc (#2265) 
Signed-off-by: chickeyton <ngton2014@gmail.com>
 2026-03-29 15:56:51 +00:00
WeiQing ChenandCanlin Guo ecfee25c3b [Bugfix] fix: handle Qwen-Image-Layered layered RGBA output for jpeg edits (#2297) 
Signed-off-by: David Chen <530634352@qq.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
 2026-03-29 11:33:37 +00:00
rongfu.lengandHongsheng Liu 9d9e6abae6 [Feat] add helios fp8 quantization (#1916) 
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
 2026-03-29 06:35:56 +00:00
TJian f5c7ecb6cc [ROCm] [CI] Migrate to use amd docker hub for ci (#2303) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-03-29 19:07:03 +13:00
Lidang Jiang 168bea2440 [Misc] Make gradio an optional dependency and upgrade to >=6.7.0 (#2221) 
Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>
Signed-off-by: Lidang Jiang <lidangjiang@gmail.com>
 2026-03-28 12:33:55 -04:00
Ding Zuhaoand汪志鹏 283a62fd76 [Feature] [HunyuanImage3] Add TeaCache support for inference acceleration (#1927) 
Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-03-28 15:24:21 +00:00
Junhong Liu a3e1322ad9 Qwen3-Omni][Bugfix] Replace vLLM fused layers with HF-compatible numerics in code predictor (#2291) 
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
 2026-03-28 23:02:44 +08:00
SYLAR ef17011086 [skip ci] [Docs]: add CI Failures troubleshooting guide for contributors (#1259) 
Signed-off-by: lishunyang <lishunyang12@163.com>
 2026-03-28 22:36:28 +08:00
lif 1414195fbb Fix: Enable /v1/models endpoint for pure diffusion mode (#805) 
Signed-off-by: majiayu000 <1835304752@qq.com>
 2026-03-28 22:17:38 +08:00
amy-why-3459 eced989b40 [Docs] Modify the documentation description for streaming output (#2300) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-03-28 11:24:15 +00:00
amy-why-3459 93bb988422 [Tests][Qwen3-Omni] Add performance test cases (#2011) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-03-28 19:01:44 +08:00
Lancer 64629cc174 [Feat] support quantization for Flux Kontext (#2184) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-03-28 10:28:10 +00:00
Ding Zuhao 5cf6870277 [Bugfix][HunyuanImage3.0] Fix default guidance_scale from 1.0 to 4.0 and port GPU MoE ForwardContext fix from NPU (#2142) 
Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
 2026-03-28 13:49:03 +08:00
Yueqian Lin f55ea28005 [Qwen3TTS][Bugfix] Replace vLLM fused layers with HF-compatible numerics in code predictor (#2277) 
Signed-off-by: linyueqian <linyueqian@outlook.com>
v0.18.0 		2026-03-28 10:47:17 +08:00
Yuanheng Zhao a353594e2e [Misc] Clean up unused diffusion timing args in examples (#2266) 
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
 2026-03-28 07:03:17 +08:00
Sy03 d9912eb6e9 [Bugfix] Fix Fish Speech S2 Pro prompt handling for truncated audio & emotion tag (#2268) 
Signed-off-by: Sy03 <1370724210@qq.com>
 2026-03-28 07:00:00 +08:00
Daniel Huang d0edd3e4e3 [bugfix] Remove duplicate yaml entry (#2279) 
Signed-off-by: Daniel Huang <daniel1.huang@intel.com>
 2026-03-28 06:59:13 +08:00
wangyu bd8b9b6142 [CI] Update pytest command to exclude specific test in nightly build (#2272) 2026-03-27 21:59:06 +08:00
Canlin Guo 3fe46360f0 [Release] Upgrade NPU dockerfile & docs for v0.18.0 (#2271) 2026-03-27 20:37:16 +08:00
bjf-frz 637abb759f [Bugfix] Modify conftest.py set unspecified parameters (#2263) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
 2026-03-27 10:33:16 +00:00
dengyunyangand汪志鹏 c0d90b64c6 [Feature] support sp for hunyuan (#2163) 
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2026-03-27 17:28:13 +08:00
Zeyu Huang | 黃澤宇Gao HanAliciaDidan Deng
 		c139ee4aed [CI] remove benchmark/testing comparison w/ other frameworks (#2179) 
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
 2026-03-27 17:26:18 +08:00
Junhong Liu c51adeacde [CI] Add online e2e test for MIMO-Audio (#2129) 
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
 2026-03-27 17:19:54 +08:00
Bingyu (Spencer) Liu 0db2b3c8f2 [CI] Add sd3 for test (#2219) 
Signed-off-by: LiuBingyu <liubingyu62@gmail.com>
 2026-03-27 08:31:56 +00:00
bjf-frz 94e6a96fb8 [Bugfix]fix_test_bagel_online (#2237) 
Signed-off-by: bjf-frz <frz123db@gmail.com>
 2026-03-27 15:20:48 +08:00
knlnguyen1802andSamit 49c1abea17 [Bugfix] Fix dynamic function call on collective_rpc of DiffusionWorker (#2217) 
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Samit <285365963@qq.com>
 2026-03-27 14:28:59 +08:00
Samit 61e0ec517d [Test] L4 complete diffusion feature test for Qwen-Image models (#1869) 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
 2026-03-27 14:03:50 +08:00
amy-why-3459 9f667ee151 [BugFix][Qwen3-Omni]Fixed the issue of incorrect answers for single words. (#2239) 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
 2026-03-27 11:46:24 +08:00
Reid 6f87a9382f Frontend] Support --dtype in qwen3_omni offline e2e script (#2246) 
Signed-off-by: reidliu41 <reid201711@gmail.com>
 2026-03-27 03:12:11 +00:00
Gao Han 4be54ccec4 [CI] Skip tests due to L3 CI failure (#2245) 
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
 2026-03-27 10:35:35 +08:00
Lancer 055963b3fd [Bugfix] Fix tp and Quantization incompatible for Flux (#2180) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-03-27 09:21:50 +08:00
Chen-Yo SunandYueqian Lin e408fd97aa [CI] Add Voxtral TTS e2e test (#2023) 
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
 2026-03-26 21:17:03 -04:00
wangyu f7107a384b [CI] Increase diffusion initialization timeout from 600 to 700 seconds in online serving tests (#2230) 
Signed-off-by: wangyu <410167048@qq.com>
 2026-03-27 08:43:58 +08:00
Peiqi Yin a67859574d [Test] L4 complete diffusion feature test for Z-Image (#2132) 
Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
 2026-03-26 18:16:08 +00:00
Cheung Ka Wai 590ab5b3e9 [Bug Fix] Resolve broken image issue when TP is enabled and no seed is provided. (#2176) 
Signed-off-by: Mike Cheung <zhtmike@gmail.com>
 2026-03-26 16:56:46 +00:00
Baoyuan Qi 66d5478dad [Compatibility] Add Multiple Attention Backends Support in MIMO-Audio Tokenizer (#2225) 
Signed-off-by: 齐保元 <qibaoyuan@xiaomi.com>
 2026-03-27 00:47:53 +08:00
Dnoob e3d178cd66 [Bugfix] Fix diffusion benchmark issues #1873 (#1897) 
Signed-off-by: Dnoob <dxpouo@gmail.com>
 2026-03-27 00:26:59 +08:00
SamitZeyu Huang | 黃澤宇gcanlin
 		d96d63cb7f [Doc] Improve diffusion generation parameter docs for online serving (#2051) 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
 2026-03-26 15:12:16 +00:00