 Wenhua Cheng
|
294fbb4f59
|
add 2/3/5/6/7 CUDA support in AutoRound format (#52890)
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
|
2026-09-07 09:59:19 +08:00 |
|
|
Jee Jee Li
|
199cb9b964
|
[Kernel] Remove unused fake implementation (#55535)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-09-06 17:54:32 -07:00 |
|
|
Jürgen Schmied
|
4df80187b5
|
[Kernel] SM 12.x blockwise FP8: swizzle the CTA raster when the weight exceeds the L2 (#55180)
|
2026-09-06 17:36:59 -07:00 |
|
|
Kevin H. LuuandCodex
|
6865e67f0b
|
[Bugfix] Defer adaptive verification until after kernel warmup (#55455)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-06 11:31:40 -07:00 |
|
|
Kevin H. LuuandCodex
|
722d169339
|
[CI] Align extraction test with canonical auxiliary layer order (#55457)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-06 11:22:14 -07:00 |
|
|
zhouyouandCursor Grok 4.6
|
52358e6e19
|
[Frontend] Expose multimodal metadata for disaggregated prefill (#54659)
Signed-off-by: zhouyou9505 <zhouyou9505@gmail.com>
Co-authored-by: Cursor Grok 4.6 <noreply@cursor.com>
|
2026-09-06 14:46:52 +00:00 |
|
|
aoshen02andCodex
|
808f8cd3ac
|
[Governance] Add aoshen02 as code owner for RL components (#55529)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-06 13:26:22 +00:00 |
|
|
Almog TavorandOr Ozeri
|
dc02934a07
|
[Bugfix][KV Offload] Stop offloading the final sampled token's KV slot (#54288)
Signed-off-by: almogtavor <almogtavor@gmail.com>
Signed-off-by: Almog Tavor <70065337+almogtavor@users.noreply.github.com>
Co-authored-by: Or Ozeri <or@ozery.com>
|
2026-09-06 15:22:19 +03:00 |
|
|
|
569adb5a97
|
[Bugfix][KV Offload] Fix SWA store reachability during chunked prefill (#54362)
Signed-off-by: Will Hampson <whamp@ggl.slmail.me>
Co-authored-by: Will Hampson <whamp@ggl.slmail.me>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-09-06 13:50:39 +03:00 |
|
|
Zupeng WangandCodex
|
dd0760165c
|
[Bugfix] Fall back to T1 when ARC cannot reclaim enough entries from T2 (#55461)
Signed-off-by: Wang Zupeng <zupenwang@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-06 13:28:19 +03:00 |
|
|
|
9afb878a55
|
[Bugfix][KV Offload] Skip cleaned-up async lookup batches (#55075)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-09-06 13:27:46 +03:00 |
|
|
SunandIsotr0py
|
a1541f5742
|
[Perf] Use SDPA for BLIP-2 Q-Former attention (#55285)
Signed-off-by: levius <2114377220@qq.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-06 07:04:19 +00:00 |
|
|
Ziming HuangandOpenAI Codex
|
144e79c810
|
[Kimi K3] Support internal prefix checkpoints with partial prefix caching and spec-decoding (#53614)
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-06 13:18:15 +08:00 |
|
|
Clinton ThomasandLucas Bourtoule
|
1970f3ed4b
|
Validate scale-out multimodal data before engine handoff (#51898)
Signed-off-by: Clinton Thomas <1033162+KernelClint@users.noreply.github.com>
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
|
2026-09-06 04:58:04 +00:00 |
|
|
Baki Burak Öğün
|
f2e2936f91
|
[Kernel] Add fused MoE tuned config for E=256,N=512 on NVIDIA A100 80GB PCIe (#55511)
Signed-off-by: Baki Burak Ogun <63836730+bakiburakogun@users.noreply.github.com>
|
2026-09-06 03:15:01 +00:00 |
|
|
zhao, zhenhui
|
1c344ed41e
|
[CPU] [Feat] Add native AMX-FP8 attention impl for Diamond Rapids (#49410)
Signed-off-by: zhejiangxiaomai <zhenhui.zhao@intel.com>
|
2026-09-06 11:06:56 +08:00 |
|
|
aoshen02
|
039ea82660
|
[Core] Sync DP state on the first step of a wave (#52957)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
|
2026-09-06 02:16:58 +00:00 |
|
|
lucamotzandOpenAI Codex
|
f4eccdadef
|
[Bugfix][Multimodal] Bound renderer warmup to the prefill token budget (#55448)
Signed-off-by: Luca Motz <luca.motz@icloud.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 16:43:28 +00:00 |
|
|
linitra24andJee Jee Li
|
7985444339
|
[Kernel][HY V4] Add Triton iHC pre/post fallback (#55059)
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-05 23:12:50 +08:00 |
|
|
|
52bc900d93
|
[Bugfix][Kernel] Build fused GDN MTP decode for SM110 (#53835)
Signed-off-by: WikAlie <194917782+wei-core@users.noreply.github.com>
Co-authored-by: WikAlie <194917782+wei-core@users.noreply.github.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-09-05 07:59:50 -07:00 |
|
|
Harry Huang
|
28e605fb33
|
[Bugfix][Qwen4Exp] fix state index strides in fused PLE conv (#55375)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
|
2026-09-05 14:02:20 +00:00 |
|
|
lucamotzandLuca Motz
|
bc96d76aa9
|
[Kernel] Fall back from persistent top-k on low-shared-memory GPUs (#54110)
Signed-off-by: Luca Motz <321921718+lucamotz@users.noreply.github.com>
Signed-off-by: Luca Motz <luca.motz@icloud.com>
Co-authored-by: Luca Motz <321921718+lucamotz@users.noreply.github.com>
|
2026-09-05 08:58:37 -04:00 |
|
|
aoshen02andaoshen02
|
7fbd44cbe0
|
[Bugfix][DSv4] Seed the -1 sentinel in the prefill sparse index workspace (#55299)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
|
2026-09-05 18:31:04 +08:00 |
|
|
Adababyandshaolila
|
2902ca17e3
|
[Bugfix] complete VLLMValidationError migration in chat_utils.py (#50254)
Signed-off-by: shaolila <shaolila@buaa.edu.cn>
Co-authored-by: shaolila <shaolila@buaa.edu.cn>
|
2026-09-05 17:56:12 +08:00 |
|
|
|
e473e9036f
|
[Docs][Models] Use the official FunASR Nano vLLM checkpoint (#54944)
Signed-off-by: LauraGPT <18321252+LauraGPT@users.noreply.github.com>
Co-authored-by: LauraGPT <18321252+LauraGPT@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 00:29:49 -07:00 |
|
|
waizuichougou
|
32601ef7a1
|
[Perf][Multimodal] Avoid duplicate text embedding in Qwen2.5-Omni (#55415)
Signed-off-by: waizuichougou <2082431897@qq.com>
|
2026-09-05 06:39:32 +00:00 |
|
|
|
8369affa54
|
[Feat] Add EPLB support for GLM-5.3-Flash (#55119)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Jared Wen <jaredwen@inferact.ai>
Co-authored-by: Jared Wen <jaredwen@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-05 05:28:33 +00:00 |
|
|
|
e962733e08
|
[Security] Validate cache salts before they reach LMCache (#51444)
Signed-off-by: Clinton Thomas <1033162+KernelClint@users.noreply.github.com>
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-05 03:56:06 +00:00 |
|
|
GroupieSteven
|
4ee2595512
|
[Attention] Sync FA with upstream (#54819)
Signed-off-by: Chuyue Wang <stevenwang0805@outlook.com>
|
2026-09-04 23:48:32 -04:00 |
|
|
|
d87a440f88
|
[Core][MRV2] Support eagle3 spec decode with pipeline parallel (#50514)
Signed-off-by: Yongqin Wang <yongqinwang@roblox.com>
Co-authored-by: Cursor <noreply@cursor.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-09-05 11:45:34 +08:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
d4ef5e53fc
|
[CI][ROCm] Disable Transformers nightly groups (#55409)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 10:51:01 +08:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
ea5f41edd7
|
[CI][ROCm] Restore Wikitext coverage for Qwen OCP-MX (#55410)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 10:50:54 +08:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
a7f9be9612
|
[CI][ROCm] Raise AMD job and server readiness timeouts (#55308)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 10:50:51 +08:00 |
|
|
Wei ZhaoandOpenAI Codex
|
16328c7a77
|
[Perf] Kimi K3 nvfp4 Align in_proj weights by 128 to avoid elementwise copy (#55242)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 10:46:47 +08:00 |
|
|
|
385ba6b5b0
|
[Bugfix][Quantization] Register Quark per-block FP8 scales as weight_scale (#54770)
Signed-off-by: jimmy-adams <41593649+jimmy-adams@users.noreply.github.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-05 10:44:24 +08:00 |
|
|
|
6cbb3c154e
|
[Perf][GDN] Build cudagraph-capture metadata without a device sync (#55404)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Roger Wang <rogerw@inferact.ai>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-09-04 17:40:17 -07:00 |
|
|
Nick Hill
|
8277c42e4c
|
[Perf] Ensure async h2d copies are pinned in more places (#55202)
|
2026-09-04 17:17:01 -07:00 |
|
|
Nathan Sala
|
874df9373d
|
[Bugfix] Preserve Mamba state for padded prompt tails (#55178)
Signed-off-by: Nathan Sala <natouda@gmail.com>
Signed-off-by: Nathan Sala <33957625+natsala13@users.noreply.github.com>
|
2026-09-04 23:44:28 +00:00 |
|
|
|
eb74fbb3e7
|
[Bugfix][NIXL] Don't assert when a failed transfer is cleaned up twice (#54518)
Signed-off-by: Yizheng Jiao <jyizheng@gmail.com>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-04 23:20:32 +00:00 |
|
|
|
685074cd61
|
[Bugfix][V2] Warm up kernels before capturing CUDA graphs (#55341)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-04 22:44:18 +00:00 |
|
|
Misha Goin
|
8f269a93bb
|
Revert "[CI] Remove deleted nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 and its arch aliases" (#55392)
|
2026-09-04 14:45:24 -07:00 |
|
|
|
3f41d102c5
|
[1/2][Model Runner V2] DBO support, eager mode (#50945)
Signed-off-by: specture724 <specture724@gmail.com>
Signed-off-by: Anjie Hou <149605198+specture724@users.noreply.github.com>
Co-authored-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-09-04 14:17:39 -07:00 |
|
|
Taneem IbrahimandHarry Mellor
|
784cac7c42
|
[Mypy] Fix mypy typing for P models (#54169)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-04 20:47:11 +00:00 |
|
|
Zihan Zhang
|
5093e4844a
|
[Bugfix][Spec Decode] Drop FlashAttention's AOT schedule for a sliding-window DFlash drafter (#54374)
|
2026-09-04 16:42:01 -04:00 |
|
|
Sun
|
c81ace1859
|
[Perf] Read VidCom2 frame budgets once (#55331)
Signed-off-by: levius <2114377220@qq.com>
|
2026-09-04 20:11:42 +00:00 |
|
|
Taneem Ibrahim
|
3284af6bf1
|
[Bugfix] Reject 0 or non-positive max concurrency (#54887)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-04 15:59:29 -04:00 |
|
|
Stefano Castagnetta
|
2524051385
|
[Bugfix][Spec Decode] Honour the draft's attention_backend on Model Runner V2 (#54826)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
|
2026-09-04 12:23:19 -07:00 |
|
|
|
5690b02c03
|
[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-04 11:46:06 -07:00 |
|
|
Andrey Talman
|
a11dfcff89
|
[CI] Surface why the CRCR nightly report cannot read its Buildkite secret (#54860)
Signed-off-by: Andrey Talman <atalman@fb.com>
|
2026-09-04 11:10:30 -07:00 |
|
|
Jared WenandKimi
|
701a744490
|
[CI] Raise AMD Spec Decode Eagle 1 job timeout to 35min (#55136)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: Kimi <noreply@moonshot.cn>
|
2026-09-04 17:31:54 +00:00 |
|