|
37c11e6e4f
|
[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#5791)
Signed-off-by: sheenlin <sheenlin@tencent.com>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: yurain <yurain26@users.noreply.github.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
|
2026-08-20 19:22:40 +00:00 |
|
|
zzh
|
b1da47b781
|
Fix npu moe registration (#6350)
Signed-off-by: zzh <943967662@qq.com>
|
2026-08-20 16:34:24 +00:00 |
|
|
Inesh Reddy Chappidi
|
cd3867c373
|
[Model] Suppress silence codec tokens for the first N Qwen3-TTS decod… (#5048)
Signed-off-by: Inesh Reddy <ineshreddy249@gmail.com>
|
2026-08-20 09:22:37 -07:00 |
|
|
amy-why-3459andCursor
|
9c61d5b67b
|
[Bugfix][MiniCPM-o] Stop Talker mid-utterance truncation and load cod… (#6346)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-08-20 11:50:07 +08:00 |
|
|
Joshna-MedisettyandCursor
|
bd17618c11
|
[XPU][Bugfix] Make Omni AR async output path device-agnostic (#5569)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-08-19 20:06:33 -05:00 |
|
|
Yukim1
|
6f55a06fab
|
[Docs] Remove stale stage config references (#6270)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
|
2026-08-20 07:09:12 +08:00 |
|
|
Thanaji Rao ThakkalapelliandChendi.Xue
|
efaf4276f9
|
[Bugfix] Record device-agnostic torch.Event on XPU to fix async D2H image corruption [XPU] (#5571)
Signed-off-by: Thanaji Rao Thakkalapelli <thanaji.rao.thakkalapelli@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
|
2026-08-19 16:30:38 -05:00 |
|
|
amy-why-3459
|
3c6648d8a5
|
[Bugfix][NPU] Break the pytest DiffusionOutput circular import (#6293)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-08-18 10:11:10 +08:00 |
|
|
Zhou248
|
5d09cf27a9
|
[MiniCPM-o][NPU] Enable MiniCPM-o Code2Wav NPUGraph replay (#5604)
Signed-off-by: Zhou248 <62542847+Zhou248@users.noreply.github.com>
|
2026-08-17 15:09:51 +08:00 |
|
|
Wenjia Li
|
8ecd1f6d5c
|
[Perf][NPU] Fuse MiniMax H3 Qwen3-VL SwiGLU (#6167)
Signed-off-by: Wenjia Li <wjialish@gmail.com>
|
2026-08-14 11:47:17 +00:00 |
|
|
Wenjia Li
|
ffd11c181e
|
[Perf][NPU] Fuse MiniMax H3 Qwen3-VL RoPE (#6061)
Signed-off-by: Wenjia Li <wjialish@gmail.com>
|
2026-08-14 09:49:26 +00:00 |
|
|
Weiming Liao
|
f41451f64c
|
[NPU] Upgrade to v0.27.0 (#6096)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
|
2026-08-13 20:01:01 +08:00 |
|
|
Zhou TaichangandClaude Opus 5
|
2ce15ab7a0
|
[Rebase] Rebase to vllm 0.27.0 (#5976)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-11 15:23:46 +00:00 |
|
|
R0CKSTAR
|
22dd96ec5c
|
[Hardware][MUSA] Complete Omni platform interfaces (#6058)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
|
2026-08-11 12:46:42 +00:00 |
|
|
|
e04210d690
|
[Hardware][MUSA] Enable Qwen3-Omni ModelOpt FP8 inference (#5671)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-08-11 17:19:09 +08:00 |
|
|
ooooooye
|
740f45abcd
|
[Perf][Diffusion] MiniMax-H3: opt into packed varlen attention on NPU to eliminate quadratic mask materialization (#5891)
Signed-off-by: brandneway <gyuan4892@gmail.com>
|
2026-08-10 19:47:03 +08:00 |
|
|
Zijun HuangandWeiQing Chen
|
93457f29ff
|
[NPU][Quantization] Add RainFusion attention and INT8 online quantization for MiniMax H3 (#5706)
Signed-off-by: Zijun Huang <zijunhua@usc.edu>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
|
2026-08-06 14:15:21 +08:00 |
|
|
GXIN
|
6a604be610
|
[Bugfix][NPU] Fallback to BSND RoPE when Qwen3-TTS short-seq BNSD li… (#5608)
Signed-off-by: XIN GAO <1037396230@qq.com>
|
2026-08-05 13:02:47 +08:00 |
|
|
Gao Han
|
78c144f3a8
|
[CI failed] Revert "[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor" (#5777)
|
2026-08-04 15:21:38 +00:00 |
|
|
|
6fdc4ca62d
|
[Perf][Qwen3-TTS] Fuse QKV and gate_up projections in code predictor (#4958)
Signed-off-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: sheenlin <sheenlin@tencent.com>
Co-authored-by: yurain <yurain26@users.noreply.github.com>
|
2026-08-04 11:59:32 +00:00 |
|
|
TJian
|
d50ea9fccc
|
[ROCm] [CI] Fix ROCm CI for v0.26.0 (#5528)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-07-30 11:27:32 +08:00 |
|
|
zzhanddengyunyang
|
dba05c3517
|
Enable Diffusion Image models asynchronous output (#4981)
Signed-off-by: zzh <943967662@qq.com>
Co-authored-by: dengyunyang <584797741@qq.com>
|
2026-07-29 17:21:55 +00:00 |
|
|
Weiming Liao
|
39663d5287
|
[NPU] upgrade to v0.26.0 (#5490)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
|
2026-07-29 11:21:04 +08:00 |
|
|
Joshna-MedisettyandChendi.Xue
|
7fa40681ff
|
Xpu/vllm 0.26 fixes (#5476)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
|
2026-07-29 08:15:36 +08:00 |
|
|
Joshna-Medisetty
|
807db6efd7
|
[Refactor] Migrate Voxtral TTS XPU stage config to --deploy-config (#5467)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
|
2026-07-28 07:35:35 +08:00 |
|
|
|
cbab1d4d8f
|
[Rebase] Rebase to vllm 0.26.0 (#5443)
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: tzhouam <tzhouam@gmail.com>
|
2026-07-27 23:35:49 +08:00 |
|
|
SYLARandlishunyang12
|
7762d664d8
|
[Attention] Add trtllm diffusion attention backend with Skip-Softmax (#5283)
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
|
2026-07-27 22:48:11 +08:00 |
|
|
Wang fuyinandHongsheng Liu
|
4dd1b47f47
|
[Config] Read stage metadata from VllmOmniConfig (#5343)
Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-07-27 22:44:06 +08:00 |
|
|
|
e108cbb510
|
[NPU][HunyuanImage3] Adapt diffusion FusedMoE for vLLM >= 0.24.0 (#5167)
Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-07-27 22:41:34 +08:00 |
|
|
|
b6c4578dac
|
[BugFix]Add MiniCPM-o 4.5 end-to-end test suite (offline, online serving) (#5237)
Signed-off-by: y_null <y_null@qq.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-07-25 17:00:13 -07:00 |
|
|
rein yangandSy03
|
ad3a162eb8
|
[perf] Minicpm o4.5 optimization (#5228)
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Co-authored-by: Sy03 <1370724210@qq.com>
|
2026-07-24 17:20:39 +08:00 |
|
|
Joshna-MedisettyandChendi.Xue
|
0fe5d73a63
|
[Bugfix][XPU] Fix free-memory abort and num_speculative_steps crash on XPU (#5330)
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
|
2026-07-23 17:17:00 +00:00 |
|
|
vOvandClaude Opus 4.8
|
cc1939120f
|
[Bugfix] Skip non-positive scheduled token spans in omni stage runners (#5269)
Signed-off-by: cr-gao <gaochenrui@sjtu.edu.cn>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-22 16:01:45 +00:00 |
|
|
Weiming Liao
|
8219c01b57
|
[Bugfix][NPU] Port OmniConnectorModelRunnerMixin to NPU runners to fix async_chunk=false full-payload hang (#5234) (#5290)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
|
2026-07-22 13:53:04 +00:00 |
|
|
Bingyu (Spencer) Liu
|
dcf8b07d39
|
[Core] Cleanup Omni connector runtime and transfer backends (#5096)
Signed-off-by: spencerr221 <liubingyu62@gmail.com>
|
2026-07-22 09:44:15 +08:00 |
|
|
fatSheepandamy-why-3459
|
5d44868e91
|
[Hardware][Ascend] Keep HiFT vocoder on NPU (#5242)
Signed-off-by: fatSheep <tzh2005t@163.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-07-21 14:30:30 +08:00 |
|
|
amy-why-3459
|
74f2742ac2
|
[Hardware][Ascend][Model] Add NPU support for MiniCPM-o 4.5 talker/vo… (#5117)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-07-20 21:45:28 +08:00 |
|
|
|
4fbbdfd250
|
[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
|
2026-07-18 09:34:33 +00:00 |
|
|
zyz111222andamy-why-3459
|
2d58070f60
|
[Hardware][Ascend][Model] Optimize Qwen3-TTS on 310P (#4841)
Signed-off-by: zouyizhou <zouyizhou@huawei.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-07-15 08:57:44 +08:00 |
|
|
NumberWan
|
fe478a95ab
|
[BugFix] Restore vllm_c IR op priority and torch.nn.RMSNorm for Qwen-Image (#4964) (#5009)
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
|
2026-07-10 17:39:07 +00:00 |
|
|
Yueqian Lin
|
da15a4cb1c
|
[Bugfix] Drop out-of-vocabulary stop ids from min-tokens masking (qwen3-tts min_tokens engine crash) (#4971)
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
|
2026-07-08 11:24:31 -07:00 |
|
|
Samit
|
b96bc5ac87
|
Support HuggingFace kernels package for native diffusion attention backends (#4926)
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
|
2026-07-08 14:34:36 +08:00 |
|
|
amy-why-3459
|
9ceca4ec85
|
[Bugfix] Fix full-payload mm splitting for dual hidden/scheduled batch axes (#4870 follow-up) (#4910)
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
|
2026-07-06 15:08:05 +08:00 |
|
|
Sy03andYueqian Lin
|
9eaca72382
|
[Perf][VoxCPM2] Add unified decode graph optimization (#4606)
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
|
2026-07-04 05:30:48 +00:00 |
|
|
Weiming Liao
|
d8db832fc2
|
[NPU] Upgrade to v0.24.0 (#4848)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
|
2026-07-03 07:01:25 +00:00 |
|
|
Jiaqian Liu
|
a25636d780
|
[NPU] Fix HunyuanImage3 MoE EP+SP parallel mapping (#4344)
Signed-off-by: Celeste-jq <591998922@qq.com>
|
2026-07-02 04:14:12 +00:00 |
|
|
Zhou Taichang
|
a560ed184d
|
[Rebase] Rebase to vllm v0.24.0 (#4709)
|
2026-06-30 19:41:06 +08:00 |
|
|
|
504698dec8
|
[Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527)
Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
|
2026-06-29 17:43:36 +02:00 |
|
|
Weiming Liao
|
724f5d132d
|
[BugFix] Restore pre-#9572 NPU graph behavior (cap cudagraph_mode to PIECEWISE) (#4674)
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
|
2026-06-29 07:54:26 +00:00 |
|
|
|
5db89b41c4
|
[Core] hunyuan-image prefetch kv (#4448)
Signed-off-by: z00806815 <zhuhonghan@huawei.com>
Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Signed-off-by: zhh <zhh@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: zhuhh97 <zhuhh97@users.noreply.github.com>
|
2026-06-25 21:31:49 +08:00 |
|