 stefankoncarevicandAndreas Karatzas
|
b369f10d5c
|
[Bugfix][ROCm][CI] Restore the DeepSeek-V4 input GEMM override point (#51821)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-12 20:33:52 -05:00 |
|
|
|
5936bac7d7
|
[Bugfix] Report FULL_ATTENTION for uniform-base UniformTypeKVCacheSpecs groups instead of UNKNOWN (#51218)
Signed-off-by: Yifan Jiang <19356972+yifjiang@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-08-13 01:25:23 +00:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
caf9e8f7d5
|
[CI] Force source builds for hybrid dependencies (#52043)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-12 18:18:17 -07:00 |
|
|
afriedri
|
98f86b9c02
|
[ROCm] [bugfix] Chunked prefill paged decode masked load perf (#50017)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
|
2026-08-12 23:04:01 +00:00 |
|
|
Wentao Ye
|
23f360edaa
|
[CI Bug] Fix ci moe test (#52009)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-12 21:28:53 +00:00 |
|
|
Yongye ZhuandKimi Code
|
025d56a11e
|
[Build] Update DeepGEMM pin to deepseek-ai nv_dev tip (#52035)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
|
2026-08-12 13:49:04 -07:00 |
|
|
Tyler Michael Smith
|
34735aceda
|
[Bugfix] Pin DeepEP by its full commit hash (#52028)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-08-12 20:01:32 +00:00 |
|
|
xiao fengandMichael Goin
|
e62abc37d4
|
[Bugfix][Kernel] Fix persistent top-k histogram reuse after short rows (#49139)
Signed-off-by: fxfxfxfxfxfxfxfx <227935476@qq.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-08-12 12:54:45 -07:00 |
|
|
|
7f7a32cfec
|
[Spec Decode] DSpark confidence-scheduled verification (#47808)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Signed-off-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-12 12:27:48 -07:00 |
|
|
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
fe889ac925
|
[K3 Perf] Flash kda out kernel for prefill, 1.1~1.4x kernel performance improvement (#51311)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-12 14:51:48 -04:00 |
|
|
|
19d61b1273
|
[Bugfix] Initialize DeepGemmQuantScaleFMT oracle lazily; bound QuantFP8 UE8M0 packed path to group_size 128 (#51359)
Signed-off-by: BabyDrangoner <148877251+BabyDrangoner@users.noreply.github.com>
Signed-off-by: kiroxu <148877251+BabyDrangoner@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-12 14:27:50 -04:00 |
|
|
stefankoncarevic
|
d20a031d33
|
[Bugfix][ROCm][MoE] Update AITER MXFP4 W4A16 tests to the renamed expert_mask (#51980)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-08-12 17:45:45 +00:00 |
|
|
Wentao Ye
|
0fb168e6ee
|
[CI Bug] Fix ci qwen3.5 (#52007)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-12 13:22:09 -04:00 |
|
|
Hongxia YangandClaude Fable 5
|
b745d08de1
|
[ROCm][K3] Dequantize the fp8 decode query for MLA backends without quant-query support - TRITON_MLA (#51860)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-12 12:40:41 -04:00 |
|
|
|
324f452f64
|
[ROCm] update triton in base docker for gluon compatibility (#51464)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-12 11:26:17 -05:00 |
|
|
Taneem Ibrahim
|
6ea6c42659
|
[Bugfix] Bound Anthropic stop sequences (#51997)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-12 12:05:12 -04:00 |
|
|
Russell BryantandClaude Opus 4.8
|
8151f2ad43
|
[Docs] Warn that --api-key does not gate all endpoints (#51999)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-08-12 08:16:35 -07:00 |
|
|
|
9035151d6c
|
[Model] Add native Dots3 NOTE multimodal support (#51255)
Signed-off-by: KurodaKanbei <mistergalahad@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-12 23:13:20 +08:00 |
|
|
Max HuandNick Hill
|
b1b752042f
|
Avoid long-blocking H2D copies in ViT (#51841)
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-12 22:54:04 +08:00 |
|
|
Kunshang Ji
|
7aa248fcfe
|
[XPU][CI/Release][2/N] add triton shim in xpu requirements (#51935)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-12 20:10:10 +08:00 |
|
|
Michael Goin
|
8e958902ee
|
[Bugfix] Disable fine-grained prefix-cache hits for incompatible hybrid KV layouts (#51843)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-12 04:08:40 -07:00 |
|
|
dmai-afk
|
4c51ceb11b
|
[Bugfix][Multimodal] Invalidate retained PyNvVideoCodec decoder after failure (#51139)
Signed-off-by: Dat Mai <dmai@nvidia.com>
|
2026-08-12 11:02:10 +00:00 |
|
|
dmai-afk
|
86e2ab50aa
|
[Bugfix][Frontend] Return 400 for invalid PyNvVideoCodec video input (#51120)
Signed-off-by: Dat Mai <dmai@nvidia.com>
|
2026-08-12 10:58:46 +00:00 |
|
|
Tan Pin Siang
|
e60f3c4c13
|
[Bugfix] Fix MiniMax-M3 compressed-tensors FP8 MoE SwiGLU params (#46845)
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com>
|
2026-08-12 10:52:30 +00:00 |
|
|
Li, Jiang
|
6accb779a3
|
[CI] Add registry layer cache to x86 CPU image build (#51911)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-08-12 17:58:01 +08:00 |
|
|
Chaojun Zhang
|
8c011da6d0
|
[XPU] Route block-quantized FP8 weights to the W8A8 kernel (#50787)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
|
2026-08-12 16:57:22 +08:00 |
|
|
HuanxingandCopilot
|
aeece10c06
|
[Bugfix][XPU] Run GDN attention as eager break under breakable cudagraph (#51928)
Signed-off-by: Huanxing <huanxing.shen@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
2026-08-12 16:23:39 +08:00 |
|
|
aoshen02
|
4eef91c03c
|
[Model] Support R3 capture with DeepGEMM MegaMoE (#51831)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
|
2026-08-12 01:07:07 -07:00 |
|
|
Xin Yang
|
10b7766a90
|
[Attention] Move context_lens_tensor compute into GDN prefill path (#51913)
Signed-off-by: Xin Yang <xyangx@amazon.com>
|
2026-08-12 15:35:44 +08:00 |
|
|
Kunshang Ji
|
10f9b5d74f
|
[CI/Release][XPU] fix workdir path for triton shim job (#51923)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-12 14:41:29 +08:00 |
|
|
Matej SirovatkaandJee Jee Li
|
3ac9525507
|
[Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074)
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-12 14:06:53 +08:00 |
|
|
Lucas WilkinsonandOpenAI Codex
|
02ac17851d
|
[Refactor][MRV2] Unify uniform decode token count helper (#51917)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-12 05:58:43 +00:00 |
|
|
aoshen02andCodex
|
f2906b492e
|
[Bugfix] Avoid repeated layerwise reload warning scans (#49505)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-08-12 13:53:50 +08:00 |
|
|
Vinay R DamodaranandClaude Opus 5
|
3ee2df3033
|
[Frontend] Make model optional on all /derender request classes (#51463)
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-12 04:48:58 +00:00 |
|
|
xiangdong
|
a53ad85913
|
[XPU][CI]Change to use global VLLM_DISABLE_COMPILE_CACHE=1 in Intel GPU CI (#51905)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
|
2026-08-12 12:30:41 +08:00 |
|
|
|
3962042304
|
[Bugfix][V1][Multimodal] Recover from P0/P1 processor cache drift (#46747) (#46747)
Signed-off-by: William Zhao <williamzh@meta.com>
Signed-off-by: WillZZZy <93454470+WillZZZy@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-12 12:06:57 +08:00 |
|
|
Kunshang JiandGitHub Copilot
|
f4e9bb01de
|
[CI/Release][1/N][XPU] Publish XPU Triton shim index (#51759)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: GitHub Copilot <copilot@github.com>
|
2026-08-12 11:45:06 +08:00 |
|
|
|
7f9173dfa2
|
[ROCm][Perf] Kimi-K3 Fused kernel for KDA decode (#50654)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-08-11 20:39:34 -07:00 |
|
|
Max HuandMax Hu
|
d462dee37d
|
[Bugfix][Triton] Make fp8_min/fp8_max constexpr in _quantize_pad_fp8_kernel (#51872)
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
|
2026-08-12 03:09:54 +00:00 |
|
|
Stellar鱼
|
3fa89225bc
|
[CI/Build] Use file rendezvous for local distributed tests (#51652)
Signed-off-by: yu-xin-c <2182712990@qq.com>
|
2026-08-12 10:48:12 +08:00 |
|
|
Matvei PashkovskiiandClaude
|
20727e2841
|
[Hardware][AMD] Enable fused bf16→fp32 router GEMM on ROCm (#50268)
Signed-off-by: Matvei Pashkovskii <mpashkov@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-12 02:46:13 +00:00 |
|
|
Nick Hill
|
f97e502969
|
[Perf] Avoid more GPU<->CPU syncs on the model execution path (#51738)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-11 19:30:34 -07:00 |
|
|
Andreas Karatzas
|
23f25aac14
|
[CI] Stabilize tensor IPC multiprocessing tests (#50804)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-12 10:16:43 +08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
f067737b2a
|
[Bugfix][TieredOffloading] : Return HIT_PENDING when KV promotion is triggered (#51840)
Signed-off-by: <>
Co-authored-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
|
2026-08-12 05:07:16 +03:00 |
|
|
Aaron HaoandClaude Opus 5
|
793ca6998a
|
[Docs][RL] Rewrite weight-transfer docs; standardize examples (#51729)
Signed-off-by: haoaaron <ahao@anyscale.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-11 18:53:15 -07:00 |
|
|
Louie Tsai
|
9b3382685e
|
[Tools] vLLM Recipes conversion : support different data types variants and strategies (#51878)
Signed-off-by: louie-tsai <louie.tsai@intel.com>
|
2026-08-12 01:42:08 +00:00 |
|
|
Micah WilliamsonandAndreas Karatzas
|
045a986f3b
|
[ROCm][CI] Speed Up ROCm Skinny GEMM Tests (reduced parameterizations, (#51877)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-12 01:40:13 +00:00 |
|
|
Simon Danielsson
|
47ececb58e
|
[Perf][ROCm] Dual-stream decode with hipgraphs (#48223)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-08-12 09:32:24 +08:00 |
|
|
PikaPikachu
|
466855a2bf
|
[ROCm] Enable DeepSeek-V4 on gfx11 (#47017)
This PR enables DeepSeek-V4 checkpoints on ROCm gfx11/RDNA devices.
Signed-off-by: Letian Kang <Letian.Kang@amd.com>
|
2026-08-12 08:55:10 +08:00 |
|
|
|
0a94d85a66
|
[Bugfix][MRV2] Require all requests to be decoding for uniform-decode dispatch (#51865)
Signed-off-by: Rahul Chalamala <22563365+rchalamala@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Rahul Chalamala <22563365+rchalamala@users.noreply.github.com>
Co-authored-by: Janelle Cai <janelle.cai@modal.com>
|
2026-08-11 17:15:06 -07:00 |
|