 Michael Goin
|
6f1355a1b7
|
[Perf] Disable DeepGEMM MoE by default when TP=8 is used (#29346)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-11-24 19:01:40 -07:00 |
|
|
Hanjie QiuandBenjamin Chislett
|
5f9679a43b
|
[Spec Decode] Add support for EAGLE3 heads that do not use_aux_hidden_states (#27688)
Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2025-11-24 20:13:12 -05:00 |
|
|
Wentao Ye
|
699bca76c0
|
[UX] Raise error for attn backend of batch invariant (#29348)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-11-24 17:49:01 -07:00 |
|
|
Michael Goin
|
c17610e2ba
|
[Bugfix] Only use triton_kernels for MXFP4 on SM90 and SM100 (#29339)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-11-24 18:22:46 -05:00 |
|
|
Yan Ma
|
3cfa63ad99
|
[XPU]fix Kimi-VL-A3B-thinking on xpu (#29309)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2025-11-24 21:02:21 +00:00 |
|
|
Chenheli HuaandRoger Wang
|
839c6b7b72
|
[Multimodal][Qwen3 Omni] Make Qwen3 Omni work with audio-in-video inputs in V1 engine. (#27721)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2025-11-24 19:24:37 +00:00 |
|
|
bnellnm
|
8f066146c3
|
[MoE][Refactor] Make select_experts a non-static method (#29067)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2025-11-24 13:38:04 -05:00 |
|
|
Laith Sakka
|
7a228b5305
|
Add option to use unbacked, and backed size obl dynamic shapes for more sounds compilation. (#26199)
Signed-off-by: Laith Sakka <lsakka@meta.com>
|
2025-11-24 10:12:41 -05:00 |
|
|
杰兮andzhyajie
|
8005e606bf
|
[Bugfix][Rocm] Fix shared expert weight loading failure in DeepSeek-MTP (#27563)
Signed-off-by: zhyajie <yajizhan@amd.com>
Co-authored-by: zhyajie <yajizhan@amd.com>
|
2025-11-24 10:16:52 +00:00 |
|
|
Roger Wang
|
0ff70821c9
|
[Core] Deprecate xformers (#29262)
Signed-off-by: Roger Wang <hey@rogerw.io>
|
2025-11-24 04:18:55 +00:00 |
|
|
|
30854783ad
|
[Model] Add OpenCUA-7B support (#29068)
Signed-off-by: lim4349 <rockmanzero@naver.com>
Signed-off-by: Zero <rockmanzero@naver.com>
Co-authored-by: Cloud User <ubuntu@a100-80g-4.novalocal>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-11-24 10:27:55 +08:00 |
|
|
Jee Jee Li
|
1073ba68b0
|
[LoRA] Optimize 3D MoE logic (#29222)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-24 10:27:23 +08:00 |
|
|
jiahancandmgoin
|
5f96c00c55
|
[Fix] Add SM check to flashinfer MOE backend (#29144)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-11-23 00:39:30 +00:00 |
|
|
Federico
|
f55c76c2b3
|
chore: add RTX_PRO_6000 GLM4.6-FP8 kernel tuning (#29240)
|
2025-11-22 08:42:48 -08:00 |
|
|
ZiTian ZhaoandCyrus Leung
|
d84d8f4429
|
Fix EVS crash when using video_embeds inputs in Qwen2.5-VL (#29232)
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-11-22 06:48:59 -08:00 |
|
|
Cyrus Leung
|
ae66818379
|
[Misc] Fix pre-commit (#29238)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-22 06:48:01 -08:00 |
|
|
Bram WastiandWentao Ye
|
5f7209a793
|
[tiny] Remove unsupported TRITON_MLA backend from batch invariance (#28832)
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-11-22 21:00:50 +08:00 |
|
|
|
6965a392a4
|
Fix: Resolve circular import in model_loader/utils.py (#29189)
Signed-off-by: nandan2003 <nandan.vallamdasu@outlook.com>
Signed-off-by: Nandan Vallamdasu <nandan.vallamdasu@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-11-22 04:58:22 -08:00 |
|
|
jinghanhu
|
988ee66b0d
|
Handle triton kernel import exception (#29062)
|
2025-11-22 10:07:50 +00:00 |
|
|
FlintyLemming
|
052950e5b3
|
Add fused MoE config for H200 E160 N192 fp8 (#29182)
Signed-off-by: FlintyLemming <admin@flinty.moe>
|
2025-11-21 17:37:51 -08:00 |
|
|
Lukas Geiger
|
d045e22dfe
|
[Model][Qwen3VL] Tune Triton w8a8 block fp8 kernel for L40s (#29217)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-21 17:30:55 -08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
3137991f55
|
[BugFix] EPLB + B200 + DeepGEMM : Handle column-major scales tensor (#29162)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
|
2025-11-21 14:28:17 -08:00 |
|
|
|
57430fc95c
|
Default model load/config/tokenizer to mistral format if relevant files exist (#28659)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-11-21 13:58:59 -08:00 |
|
|
Ning Xie
|
53a1ba6ec5
|
[log] add weights loading time log to sharded_state loader (#28628)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
|
2025-11-21 21:06:09 +00:00 |
|
|
Lucas Wilkinson
|
1840c5cb18
|
[BugFix] Make sure to allocate worst case MoE workspace during profile run in the DP + EP case (#27426)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-11-21 11:41:52 -08:00 |
|
|
Mingyuan Maandmgoin
|
b4c8fbaae2
|
Add TRTLLM MoE NVFP4 kernel to CompressedTensorsW4A4MoeMethod (#28892)
Signed-off-by: mingyuanm <mingyuanm@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-11-21 09:54:11 -07:00 |
|
|
rasmithandRandall Smith
|
e99e467384
|
[CI/Build][Kernel][AMD] Move extra dim to after load in _fwd_kv_parallel in lighting_attn.py (#29132)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
|
2025-11-21 11:53:09 -05:00 |
|
|
Wentao YeandNick Hill
|
a42ab317ac
|
[Log] Optimize startup log (#28948)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
|
2025-11-21 08:46:20 -08:00 |
|
|
Aleksandr MalyshevandAleksandr Malyshev
|
b7f1f490a6
|
Upstream triton fp4 weight preshuffle (#28888)
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
|
2025-11-21 11:34:46 -05:00 |
|
|
Russell Bryant
|
cca2d2cdbe
|
[Core] Align whisper closer to other multimodal models (#27292)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2025-11-21 12:01:54 +00:00 |
|
|
Cyrus Leung
|
aab0102a26
|
[V0 deprecation] Remove more V0 references (#29088)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-11-21 11:56:59 +00:00 |
|
|
|
8ac3a41487
|
[CI Failure] Fix Gemma3 RoPE configuration for sliding attention layers (#29111)
Signed-off-by: Huamin Li <3ericli@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-11-20 23:53:30 -08:00 |
|
|
Cyrus LeungandHarry Mellor
|
0e741c12e3
|
[Bugfix] Fix Plamo3 rope handling (#29092)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-11-21 11:38:35 +08:00 |
|
|
Wentao Ye
|
56669c1f29
|
[CI] Fix mypy for vllm/v1/worker (#29037)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-11-21 11:36:07 +08:00 |
|
|
Hongxia Yang
|
3f5f36da3f
|
[ROCm] Fix for import when building with upstream triton for gfx1100 for gpt-oss serving (#29127)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
|
2025-11-21 03:30:07 +00:00 |
|
|
Wentao Ye
|
e1eefa4c40
|
[Bug] Fix torch warning of tf32 usage (#29112)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-11-21 01:54:59 +00:00 |
|
|
Jee Jee Li
|
9875be6431
|
[LoRA][2/2]Remove LoRA extra vocab (#28545)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-11-21 09:46:43 +08:00 |
|
|
Wentao Ye
|
df44df0143
|
[Feature] Shared Experts Overlap with FI deepgemm swap kernel, 2.2% throughput improvement and 3.6% TTFT improvement (#28879)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-11-20 18:41:49 -07:00 |
|
|
Fanli Lin
|
a2e9ebe9e2
|
[BugFix] Fix flash_attn import in siglip2navit.py (#29082)
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
|
2025-11-20 12:14:29 +00:00 |
|
|
Zhewen Li
|
93c8672ceb
|
[Bugfix] Fix spec decode memory regression after #28549 (#28819)
Signed-off-by: zhewenli <zhewenli@meta.com>
|
2025-11-20 19:05:50 +08:00 |
|
|
Shinichi Hemmi
|
c9e093116c
|
[MODEL] Implement plamo3 (#28834)
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
|
2025-11-20 03:00:19 -08:00 |
|
|
Pleaplusone
|
06c20c9904
|
[ROCm] Add AMD GPU support on Deepseek v3.2 and SparseMLA (#26670)
Signed-off-by: ganyi <ygan@amd.com>
|
2025-11-20 02:54:01 -08:00 |
|
|
Anna ShorsandChen Zhang
|
6eb745d9bd
|
Add truncate arg to yarn to match openai implementation of gpt-oss (#28244)
Signed-off-by: ashors1 <ashors@nvidia.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
|
2025-11-20 18:53:50 +08:00 |
|
|
DezhanandDezhan Tu
|
dc45efc8ef
|
[BugFix] Fix Llama4 Pipeline Parallelism Assert Error (#28577)
Co-authored-by: Dezhan Tu <dztu@meta.com>
|
2025-11-20 02:52:36 -08:00 |
|
|
Wentao Ye
|
2c52c7fd9a
|
[Bug] Fix torch dynamo warning Dynamo detected a call to a functools.lru_cache (#29038)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-11-20 16:52:23 +08:00 |
|
|
Pleaplusone
|
7218f83992
|
[ROCm][BugFix] Fix shared expert loading error when disable VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS (#28633)
Signed-off-by: ganyi <ygan@amd.com>
|
2025-11-20 14:50:23 +07:00 |
|
|
Lukas Geiger
|
a9705a290a
|
[Model][QwenVL] Replace torch.repeat_interleave with faster np.repeat (#28964)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2025-11-19 22:04:23 -08:00 |
|
|
Isotr0pyandCyrus Leung
|
64192d5624
|
[Bugfix] Revert custom attention mask for gemma3-mm (#28995)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-11-20 13:23:22 +08:00 |
|
|
Shengliang Xu
|
a8c536829c
|
Consolidate Nvidia ModelOpt quant config handling for all quantization methods (#28076)
Signed-off-by: Shengliang Xu <shengliangx@nvidia.com>
|
2025-11-19 22:39:36 -05:00 |
|
|
liangel-02
|
1d642872a2
|
[torchao] fix safetensors for sharding (#28169)
Signed-off-by: Angel Li <liangel@meta.com>
|
2025-11-19 16:39:45 -08:00 |
|