11541 Commits

Author SHA1 Message Date
Driss Guessous
3fd74189db
Fixes bench (#29058)
Signed-off-by: drisspg <drisspguessous@gmail.com>
2025-11-20 21:21:54 +00:00
rasmith
5e5a7eb16f
[CI/Build] Make test_attention_selector.py run tests on correct platform (#29064)
Signed-off-by: Randall Smith <ransmith@amd.com>
Signed-off-by: rasmith <Randall.Smith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-11-20 20:45:56 +00:00
rasmith
3d84ef9054
[CI/Build][AMD] Skip if flash_attn_varlen_func not available in test_aiter_flash_attn.py (#29043)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
2025-11-20 20:39:49 +00:00
Software Developer
4d01b64284
[Bugfix] - Add Trace Headers to Beam Search Path (#29100)
Signed-off-by: dsuhinin <suhinin.dmitriy@gmail.com>
2025-11-20 20:00:33 +00:00
Kevin H. Luu
114b0e2500
[chore] Update annotate release scripts (#29077)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
2025-11-20 10:22:40 -08:00
Or Ozeri
647464719b
[KVConnector][Core] Support cross-layer KV blocks (#27743)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2025-11-20 19:09:59 +01:00
Pan Li
e5bfcb6a88
[BugFix][PD]: make example proxy usable with P2pNcclConnector (#26628)
Signed-off-by: PAN <1162953505@qq.com>
2025-11-20 17:38:31 +00:00
Alexei-V-Ivanov-AMD
22924383e1
Updating the mirror of test-amd.yaml as of 2025-11-18 (#29016)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
2025-11-20 12:07:06 -05:00
rookie
56f45eddaf
[Frontend] Optimize beam search loop by sorting and then splicing (#19347)
Signed-off-by: zhangguozhu <zhangguozhu@360.cn>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: zhangguozhu <zhangguozhu@360.cn>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-11-20 09:02:30 -08:00
TJian
82b05b15e6
[BugFix] [FEAT] Enable fastsafetensors for ROCm platform (#28225)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-11-20 16:34:11 +00:00
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
Samit
371b1d4c61
[RL] Add Pause and Resume Generation for Asynchronous RL Training (#28037)
Signed-off-by: SamitHuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
Signed-off-by: samithuang <285365963@qq.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-11-20 03:01:03 -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
Or Ozeri
c0c2dd1e0b
[BugFix] kv_offloading: Fix bug in loading of partial cpu blocks (#28951)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-11-20 18:55:10 +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 Shors
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
cjackal
66483a9d00
[Chore] Update xgrammar version from 0.1.25 to 0.1.27 (#28221)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
2025-11-20 02:53:09 -08:00
Jinzhen Lin
edfe867208
[Misc] don't cache CUTLASS_REVISION var in CMakeLists.txt (#28518)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2025-11-20 02:52:53 -08:00
Dezhan
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
Vensen
fb8851f254
[Bugfix][cache_kernels]: Fix OOB in cache_kernels.cu (#28760)
Signed-off-by: vensen <vensenmu@gmail.com>
Signed-off-by: Vensenmu <vensenmu@gmail.com>
2025-11-20 02:52:02 -08:00
Boyuan Feng
a903d59ffa
cleanup at::Tag::needs_fixed_stride_order (#28974)
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-11-20 02:51:36 -08:00
rasmith
322cb02872
[CI/Build][AMD] Fix import errors in tests/kernels/attention (#29032)
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
2025-11-20 17:48:09 +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
Bradley D
1e1c06789e
[ci][amd] fix EPLB execution test (#28742)
Signed-off-by: Bradley Davis <bradleyhd@meta.com>
2025-11-20 14:53:38 +07:00
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
Cyrus Leung
20e4497be2
[V0 Deprecation] Remove num_lookahead_slots (#29000)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-11-20 06:39:10 +00:00
Quentin Gallouédec
1c7bcc55b8
[Frontend] Allow parsed tool arguments (#28820)
Signed-off-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-11-19 22:20:12 -08:00
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
Isotr0py
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
Canlin Guo
fe25772aa9
[Bugfix] Handle broken frames in video loading (#29001)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: 凌葭 <lvjiang.lj@alibaba-inc.com>
Co-authored-by: 凌葭 <lvjiang.lj@alibaba-inc.com>
2025-11-20 04:38:12 +00:00
prashanth058
0cca9b4d13
[Bugfix] Fix precision loss in LoRA-wrapped RowParallelLinear by fusing bias into GEMM (#28972)
Signed-off-by: prashanth058 <prashanth.dannamaneni@uipath.com>
2025-11-20 03:50:37 +00:00
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
Benjamin Chislett
fcbcba6c70
[Feat] Iteration-level profiling for Torch and CUDA profiler (#28987)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-11-19 19:17:48 -08:00
Fadi Arafeh
3168285fca
[cpu][ci] Add initial set of tests for Arm CPUs (#28657)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2025-11-20 02:37:09 +00:00
Qiang Zhang
3fb0d90999
[AMD] Use Decoupled Kernel Block Size to Support AITER MLA block_size=1 (#27715)
Signed-off-by: chiangzhang <chiangzhang@tencent.com>
2025-11-20 02:11:52 +00:00
Kuntai Du
05c2dee7e9
[DeepSeek + LMCache Multiprocess] handle MLA for deepseek model + LMCache Multiprocess connector (#29039)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
2025-11-20 01:40:49 +00:00
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
Nick Hill
9ccef8e333
[Misc] Colorize logs (#29017)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-11-19 19:26:04 -05:00
Jialin Ouyang
537cc635c7
[GC Debugger] Simply and improve GC Debugger Utils (#29029)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-11-20 00:10:22 +00:00
Wentao Ye
5031cd5d55
[Refactor] Optimize select_experts (#28069)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-11-19 18:53:15 -05:00
Alexander Matveev
3aaa94ac99
[Performance] Reduce DeepGEMM N dim restriction from 128 to 64 multiplier (#28687)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-11-19 15:47:13 -08:00
JartX
8e38e99829
[Feature] EPLB on Qwen3VLMoe and CompressedTensorsWNA16MoEMethod (#28849) 2025-11-19 18:30:08 -05:00
Wentao Ye
0075bfffd4
[CI] Fix precommit rope_theta issue (#29040)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-11-19 14:22:43 -08:00
Max Hu
cb0a7b4bea
[Bugfix] Move flashinfer kernel check into ``__init__` function of `FusedMoE`` (#29018)
Signed-off-by: Max Hu <hyoung2991@gmail.com>
2025-11-19 21:54:15 +00:00
Lucas Wilkinson
8f4f77a727
[BugFix] Fix false assertion with spec-decode=[2,4,..] and TP>2 (#29036)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-11-19 13:43:54 -08:00
Micah Williamson
22e44ad589
[ROCm][CI] Fix Weight Loading With Multiple GPU Tests on ROCm (#28984)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2025-11-19 21:31:33 +00:00
Yongye Zhu
88f5b19f0b
[DeepSeek] Fix DeepSeek V3.2 Rope Embedding (#28968)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
2025-11-19 16:30:04 -05:00
Shu Wang
613abb50d5
[MoE] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#25990)
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-11-19 13:29:06 -08:00
Julien Denize
cdeec2e606
[BugFix] Ray with multiple nodes (#28873)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
2025-11-19 21:20:58 +00:00