 LancerandDidan Deng
|
c6b7597126
|
[Feat] support TP for GLM-Image (#1918)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-24 11:44:47 +08:00 |
|
Alicia
|
b0efb6ede0
|
[Doc] Sync and fix. (#2110)
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
|
2026-03-24 03:20:50 +00:00 |
|
  
|
9bf8f8ce79
|
[model] support FLUX.1-Kontext-dev (#561)
Signed-off-by: Lancer <maruxiiang6688@gmail.com>
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Signed-off-by: Lancer <402430575@qq.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Lancer <maruxiiang6688@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
|
2026-03-23 17:17:58 +00:00 |
|
Juan Pablo Zuluaga
|
ec6ee1e336
|
[Bugfix][Chunk Transfer Adapter] deque mutated fix (#2102)
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
|
2026-03-23 13:09:04 -04:00 |
|
Didan Deng
|
5aef6b9c71
|
[Bugfix] Fix Qwen-Image SP and TeaCache incompatibility (#2101)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-24 00:23:27 +08:00 |
|
Didan Deng
|
1f5eca5686
|
[Perf] Qwen-Image Performance Nightly CI test (#1805)
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-24 00:19:20 +08:00 |
|
 Megha AgarwalandZhou Taichang
|
9eeac248f2
|
[Feat] Phase 1 foundation types for multimodal output decoupling (#1816)
Signed-off-by: Megha Agarwal <agarwalmegha1308@gmail.com>
Signed-off-by: Megha Agarwal <agarwalmegha@microsoft.com>
Co-authored-by: Zhou Taichang <tzhouam@connect.ust.hk>
|
2026-03-23 22:33:01 +08:00 |
|
 汪志鹏andDidan Deng
|
77d773ad47
|
[Bagel]: Support SP (#1903)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-23 21:52:50 +08:00 |
|
WeiQing Chen
|
d6b55b9196
|
[Quantization] feat: add qwen-image gguf adapter (#1755)
Signed-off-by: David Chen <530634352@qq.com>
|
2026-03-23 13:24:54 +00:00 |
|
 
|
61cd532cff
|
[Refactor] Refactor Diffusion Scheduler/Executor Boundaries and Request State Flow (#1625)
Signed-off-by: jader <yjader@foxmail.com>
Signed-off-by: JiangJie Zhang <76905040+yJader@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-23 20:25:32 +08:00 |
|
knlnguyen1802
|
65d76a4127
|
[Feature][RL] Support batching for QwenImage in async mode (#1593)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
|
2026-03-23 10:08:24 +00:00 |
|
Y. Fisher
|
560023d5d1
|
[Bugfix] Fix NPU Hunyuan fused MoE forward context after rebase to 0.18.0 (#2091)
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
|
2026-03-23 09:22:06 +00:00 |
|
WeiQing Chen
|
602f831068
|
[Bugfix] fix gguf TypeError: GGUFConfig.get_name() missing 1 required positional argument: 'self', test: add diffusion gguf unit coverage (#1865)
Signed-off-by: David Chen <530634352@qq.com>
|
2026-03-23 14:56:15 +08:00 |
|
 zhou zhuoxinand汪志鹏
|
b147553d67
|
[Feature] add Tensor Parallelism to Omnigen2 (#2065)
Signed-off-by: zhou zhuoxin <zhouzhuoxin1508@outlook.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
|
2026-03-23 11:46:58 +08:00 |
|
Lancer
|
0833470d41
|
[Feat] support TeaCache for Flux2 klein (#1234)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
|
2026-03-23 10:19:25 +08:00 |
|
Yupu
|
cb6d012d91
|
[BugFix]: Fix OmniGen2 Model Loading (#1711)
Signed-off-by: Yupu <feng.yu.pu0330@gmail.com>
|
2026-03-22 23:13:13 +08:00 |
|
Alex Brooks
|
a8f1394699
|
[Core] Simplify OmniModelConfig Initialization (#1768)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
|
2026-03-22 18:27:28 +08:00 |
|
 LancerandHongsheng Liu
|
d8b35035ec
|
[Bugfix] Fix cache-dit for single-transformer Wan2.2 models(eg. Wan2.2-TI2V-5B) (#1392)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-22 17:57:28 +08:00 |
|
 zJandSamit
|
af9368d109
|
[Fix] Fix non-unique request IDs in /v1/images/edits endpoint (#2050)
Signed-off-by: zJ_ <19760191+zJuuu@users.noreply.github.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
|
2026-03-22 09:13:01 +00:00 |
|
Du Bin
|
b4a96b0db4
|
[Bugfix] Restore chunk-waiting requests on OmniNewRequestData rewrap failure (#1691)
Signed-off-by: dubin555 <dubin555@gmail.com>
Signed-off-by: OSS Scout <scout@oss-scout.local>
|
2026-03-22 14:32:51 +08:00 |
|
Chendi.Xue
|
28aee51a59
|
[FP8] enable hunyuan-image-3 diffusion model with fp8 online quant (#1935)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
|
2026-03-22 13:02:16 +08:00 |
|
SYLAR
|
a2a23a1499
|
[Bugfix] Fix HunyuanVideo-1.5 CI failures (#2066)
Signed-off-by: lishunyang <lishunyang12@163.com>
|
2026-03-22 17:10:55 +13:00 |
|
汪志鹏
|
1bd1d9d618
|
Remove mm_prefix_lm patch because vllm==0.18.0 already support (#2062)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
|
2026-03-21 22:32:00 +08:00 |
|
Yueqian Lin
|
15f9d60dd4
|
[Bugfix] Fix Fish Speech and CosyVoice3 online serving - missing is_comprehension and broken model detection (#2058)
Signed-off-by: linyueqian <linyueqian@outlook.com>
|
2026-03-21 22:18:10 +08:00 |
|
 
|
6838533998
|
[Model] Add HunyuanVideo-1.5 T2V and I2V support (#1516)
Signed-off-by: lishunyang <lishunyang12@163.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-21 21:26:39 +08:00 |
|
 Zhou Taichangandgcanlin
|
a90a7690b8
|
[Rebase] Rebase to vllm v0.18.0 (#2037)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-21 20:37:38 +08:00 |
|
 Juan Pablo ZuluagaandJuanPZuluaga
|
8e12007ac1
|
[BugFix][Qwen3TTS] CodePredictor CudaGraph Pool (#2059)
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
|
2026-03-21 19:11:34 +08:00 |
|
 Zeyu Huang | 黃澤宇andSamit
|
da21e991cc
|
[bugfix] /chat/completion doesn't read extra_body for diffusion model (#2042)
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Samit <285365963@qq.com>
|
2026-03-21 15:53:04 +08:00 |
|
 Sy03andsy0307
|
072647eeb2
|
[Perf] Improve Fish Speech S2 Pro inference performance (#1859)
Signed-off-by: sy0307 <sy0307@users.noreply.github.com>
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: sy0307 <sy0307@users.noreply.github.com>
|
2026-03-21 01:15:02 -04:00 |
|
NumberWan
|
7007217d4b
|
[Bugfix]: fixed ServerDisconnectedError in benchmark test (reapply #1683, fixes #1374) (#1841)
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
|
2026-03-21 11:41:02 +08:00 |
|
Chen-Yo Sun
|
95018c536a
|
[Voxtral TTS] Remove redundant yaml (#2056)
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
|
2026-03-20 14:02:35 -07:00 |
|
Lancer
|
b33d7637de
|
[Bugfix] Z-Image CFG threshold should be > 0 instead of > 1 (#1634)
Signed-off-by: Lancer <maruixiang6688@gmail.com>
|
2026-03-20 20:13:10 +08:00 |
|
Junhong Liu
|
6901ba426e
|
[Fixbug][Perf] Qwen3-omni: code predictor with re-prefill + SDPA and eliminate decode hot-path CPU round-trips (#2012)
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
|
2026-03-20 19:33:52 +08:00 |
|
Wu JIAZHEN
|
da7a8f8014
|
reafator pipeline stage/step pipeline (#1368)
Signed-off-by: asukaqaq-s <1311722138@qq.com>
|
2026-03-20 19:21:50 +08:00 |
|
Zhou Taichang
|
05d8de813e
|
[Bugfix] Remove duplicated config keyword max batch size (#1851)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
|
2026-03-20 16:13:24 +08:00 |
|
 Juan Pablo ZuluagaandJuanPZuluaga
|
b4342fb487
|
[Optim][Qwen3TTS][CodePredictor] support torch.compile with reduce-overhead and dynamic False (#1913)
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Signed-off-by: JuanPZuluaga <juanz9312@gmail.com>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
|
2026-03-20 12:12:12 +08:00 |
|
   
|
81a90d24ef
|
[Feat][Qwen3TTS][Code2wav] triton SnakeBeta and Cuda Graph (#1797)
Signed-off-by: pablo <pablo@agigo.ai>
Signed-off-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: pablo <pablo@agigo.ai>
Co-authored-by: JuanPZuluaga <juanz9312@gmal.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
|
2026-03-20 12:11:37 +08:00 |
|
Yuanheng Zhao
|
6ac7ba692d
|
[Feat] Support T5 Tensor Parallelism (#1881)
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
|
2026-03-20 08:49:01 +08:00 |
|
Chen-Yo Sun
|
e9fe78e28c
|
[Model] Add Voxtral TTS model (#1803)
Signed-off-by: Chen-Yo Sun <chenyo.sun@mistral.ai>
|
2026-03-19 16:02:11 -04:00 |
|
 
|
b766c4702c
|
Int8 Quantization Support for DiT (Z-Image & Qwen-Image) (#1470)
Signed-off-by: juboyu <767868009@qq.com>
Signed-off-by: JuboYu <767868009@qq.com>
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
|
2026-03-19 22:58:29 +08:00 |
|
 Hui.andAlvisGong
|
99cc76690d
|
[Bugfix]Fix bug of online server can not return mutli images (#2007)
Signed-off-by: Hui <1779066624@qq.com>
Co-authored-by: AlvisGong <gwly0401@163.com>
|
2026-03-19 03:57:04 -07:00 |
|
rein yang
|
60a8c01a96
|
[Bugfix] revert PR#1758 which introduced the accuracy problem of qwen3-omni (#2009)
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
|
2026-03-19 17:34:01 +08:00 |
|
Ziming Huang
|
89fff09628
|
[Fix] Fix slow hasattr in CUDAGraphWrapper.__getattr__ (#1982)
Signed-off-by: ZeldaHuang <hzm414167@alibaba-inc.com>
|
2026-03-19 17:10:08 +08:00 |
|
 Chendi.XueandHongsheng Liu
|
ba5a66b15b
|
[XPU] update bagel modeling to remove cuda hardcode, add xpu stage_config (#1931)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-19 16:55:16 +08:00 |
|
rongfu.leng
|
f9268822cd
|
[Bugfix] fix helios video generate use cpu device (#1915)
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
|
2026-03-19 16:51:45 +08:00 |
|
Dnoob
|
48b3969717
|
[Bugfix] Fix Ovis Image crash when guidance_scale is set without negative_prompt (#1956)
Signed-off-by: Dnoob <dxpouo@gmail.com>
|
2026-03-19 16:51:02 +08:00 |
|
 SamitandHongsheng Liu
|
5699fe7a96
|
[Bugfix] Fix config misalignment between offline and online diffusion inference (Wan2.2, Qwen-Image series) (#1979)
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-03-19 16:00:26 +08:00 |
|
Dom Brown
|
31c8cb22cf
|
[Perf] [Qwen3-TTS] Keep audio_codes and last_talker_hidden on GPU to eliminate per-step sync stalls (#1985)
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
|
2026-03-19 13:50:26 +08:00 |
|
 
|
fde4808723
|
[Performance] diffusion timing (#1757)
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
Co-authored-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: Didan Deng <33117903+wtomin@users.noreply.github.com>
|
2026-03-19 12:26:12 +08:00 |
|
 Joshna-Medisettyandgcanlin
|
ca6c7ad2be
|
Fix OmniGen2 transformer config loading for HF models (#1934)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
|
2026-03-19 10:21:54 +08:00 |
|