|
5d09eb2cf3
|
[Bugfix][MoE] Preserve unquantized weight storage on ROCm (#46009)
Signed-off-by: bingzhaodong <aaab8b@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Zhaodong Bing <zhaobing@smc300x-ccs-aus-gpuf2c5.prov.aus.ccs.cpe.ice.amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Zhaodong Bing <zhaobing@smc300x-ccs-aus-gpuf2a0.prov.aus.ccs.cpe.ice.amd.com>
|
2026-09-03 11:06:09 +08:00 |
|
|
Kevin H. LuuandKimi Code
|
6c6376a09e
|
[CI] Remove deleted nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 and its arch aliases (#55026)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-09-02 15:18:46 -07:00 |
|
|
Wentao Ye
|
a56654d6de
|
[K3 Perf] Enable DSV3 GEMM for inner-contiguous and row-strided tensors, 12%~81% kernel performance improvement (#54565)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-02 12:22:40 -07:00 |
|
|
Luke Alonso
|
1945a94575
|
[Bugfix][Tests] Stabilize B12X linear kernel checks (#54996)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
|
2026-09-02 18:46:08 +00:00 |
|
|
stefankoncarevic
|
9b38e3ad53
|
[CI][MoE] Moe kernels test cleanup (#54954)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
|
2026-09-02 13:31:36 -05:00 |
|
|
stefankoncarevic
|
3e9d364ff7
|
[CI/Build][ROCm] Guard the two CUDA-only tests in test_bf16_skinny_gemm (#54984)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-09-02 13:21:18 -05:00 |
|
|
stefankoncarevic
|
2691c6cc53
|
[Bugfix][CI] Set cudagraph_mode=FULL for the Ernie4.5-VL ViT cudagraph test (#54957)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
|
2026-09-02 13:18:56 -05:00 |
|
|
|
bf7a14d307
|
[CI][ROCm] Add DSpark evals (#54852)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 13:14:32 -05:00 |
|
|
Isotr0py
|
1356635d83
|
[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-02 11:09:09 -07:00 |
|
|
fxmarty-amd
|
488e6fd53c
|
[CI] Revert flaky test_quark_int8_w8a8_moe (#54991)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-09-02 13:58:14 -04:00 |
|
|
Hung Hoang (黄兴）andCyrus Leung
|
3b45d053b4
|
[Bugfix][Model] Fix CohereASR streaming audio-token estimate (unit + subsampling) (#53829)
Signed-off-by: hungh <hungh@nvidia.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-02 08:55:16 -07:00 |
|
|
Ilia Yastrebov
|
41848caa63
|
[NIXL] Use int32 array for indices to avoid intermediate conversion (#51952)
Signed-off-by: Ilia Yastrebov <iyastrebov@nvidia.com>
|
2026-09-02 16:30:16 +02:00 |
|
|
waizuichougou
|
c6bca6e585
|
[Bugfix][Multimodal] Scope cache hash kwargs by modality (#54918)
Signed-off-by: waizuichougou <2082431897@qq.com>
|
2026-09-02 14:20:26 +00:00 |
|
|
Misha GoinandOpenAI Codex
|
872084fb77
|
[CI] Add Kimi-K3-pruned75-DSpark-TP4 gsm8k eval (#54817)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-02 10:18:38 -04:00 |
|
|
drakoshaandClaude
|
ba6c60e98f
|
[Bugfix][KV Offload] Scale UniformTypeKVCacheSpecs groups by DCP (#50883)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-02 17:11:48 +03:00 |
|
|
AlexHuangandOpenAI Codex
|
35faf957d6
|
[Bugfix][KV Offload] Ignore stale async lookup results (#54872)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-02 17:10:26 +03:00 |
|
|
|
ffe3bb3c72
|
[Hardware][XPU] Register matmul and linear batch-invariant kernels for XPU (#49209)
Signed-off-by: tzielinski-habana <tomasz.zielinski@intel.com>
Signed-off-by: Tomasz Zielinski <85164140+tzielinski-habana@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-02 13:31:38 +00:00 |
|
|
fxmarty-amd
|
7894394b07
|
[Online quantization] Add targeted online quantization configuration based on user patterns (#51285)
|
2026-09-02 08:55:15 -04:00 |
|
|
Cheng RuiandCodex
|
2a4e3cc3db
|
[Bugfix][KV Offload] Ensure tracker progress for oversized offers (#54759)
Signed-off-by: Cheng Rui <286040359@qq.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-02 14:09:29 +03:00 |
|
|
Nicolò Lucchesiandcjackal
|
f81eb41934
|
[Bugfix] adjust_dcp_kv_cache_interleave_size for NixlConnector only (#54803)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
|
2026-09-02 12:31:14 +02:00 |
|
|
Kevin H. Luu
|
76ba32160a
|
[CI] Shard CPU jobs above the 24h P90 threshold (#54751)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-09-02 02:16:05 -07:00 |
|
|
jackLeiandOpenAI Codex
|
584e8f0dda
|
[Model] Fix GLM-OCR MTP weight loading (#49869)
Signed-off-by: jackLei0901 <42642542+jackLei0901@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 08:38:36 +00:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
87deddc7a4
|
[CI][Spec Decode] Add MTP placeholder-token regression coverage (#54893)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 03:29:38 -05:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
c6005000d3
|
[CI][ROCm] Prefetch safetensors weights in AMD CI (#54898)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 03:28:39 -05:00 |
|
|
stefankoncarevic
|
62588e0592
|
[CI] Batch the swap_blocks verification instead of copying block by block (#54558)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
|
2026-09-02 03:12:40 -05:00 |
|
|
Kevin H. Luu
|
1b4b2a18b8
|
[CI] Shard H100 MoE refactor integration tests (#52352)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-09-02 01:10:14 -07:00 |
|
|
|
df09c76735
|
[KV Connector][Offloading] Look through UniformTypeKVCacheSpecs in the canonical portability gate (#51690)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-02 10:43:26 +03:00 |
|
|
Yusuke OdaandChauncey
|
798b557e06
|
[Frontend] Add site-packages support for reasoning/tool parser plugins (#45241)
Signed-off-by: odashi <yusuke.oda@predicate.jp>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-09-02 07:41:13 +00:00 |
|
|
Thien Tran
|
f4e6136146
|
[Kimi-K3] Bump FlashKDA to fix unstable inverse (#54859)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-09-02 00:16:29 -07:00 |
|
|
Francisco Javier Arceo
|
c00091e026
|
[Frontend] Gate scale-out endpoints behind opt-in flag (#54579)
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
|
2026-09-02 14:31:14 +08:00 |
|
|
Flora Feng
|
300f688321
|
[Bugfix] Implicitly close DeepSeek DSML parameters (#54838)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-09-02 14:13:36 +08:00 |
|
|
Qiming Zhang
|
aae36577fb
|
[XPU][UT] skip fp8_per_channel test on XPU (#54861)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-09-02 13:17:10 +08:00 |
|
|
Thien TranandCodex
|
f870b92976
|
[Qwen3.8-Flash-Next] Fuse Qwen4Exp PLE kernels (#54517)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Codex <codex@openai.com>
|
2026-09-02 12:32:16 +08:00 |
|
|
Harry Huang
|
1e300895ac
|
[Qwen4] validate FP8 PLE weight scale after loading (#54722)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
|
2026-09-02 04:30:58 +00:00 |
|
|
|
ee3c00bbf4
|
[Performance] Register Triton W4A16 GEMM as a custom op (#51453)
Signed-off-by: giuseppegrossi <ggrossi@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-01 22:55:34 -05:00 |
|
|
Yongye ZhuandOpenAI Codex
|
3ba9907a1d
|
[Kimi-K3] Overlap low-M TP8 KDA projections (#54697)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 03:35:28 +00:00 |
|
|
|
12b9573c98
|
[Bugfix][KV Offloading] Fix eager SimpleCPUOffload cache registration and final flush (#53532)
Signed-off-by: maithilijoshi20 <maithilijoshi2003@gmail.com>
Signed-off-by: maithilijoshi20 <97733343+maithilijoshi20@users.noreply.github.com>
Co-authored-by: maithilijoshi20 <maithilijoshi2003@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-09-02 03:23:09 +00:00 |
|
|
|
46c8a161f4
|
[Bugfix] Handle padded routes in CUTLASS MoE permutations (#54747)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-09-01 19:08:17 -07:00 |
|
|
Thien Tran
|
003e34341a
|
[Qwen3.8-Flash-Next] Separate prefill and decode paths for QSA indexer (#54513)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-09-02 09:08:10 +08:00 |
|
|
Andreas Karatzas
|
e01d4acbb1
|
[ROCm][CI] Handle tied experts in softplus sqrt top-k test (#52679)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-01 18:04:14 -05:00 |
|
|
mingg26andOpenAI Codex
|
259a209bfa
|
[Kimi-K3][Perf] Prefetch ll_bf16 router weights for M=1 (#53524)
Signed-off-by: ming <ming@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-01 21:40:19 +00:00 |
|
|
Nick Hill
|
a56e74afd6
|
[CI] Remove MRV2-specific tests (#54823)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-01 14:15:12 -07:00 |
|
|
Wentao Ye
|
fc72fc39ac
|
[Kimi Bug] Fix cannot access local variable 'active_non_spec_mask_cpu' (#54781)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-01 21:08:50 +00:00 |
|
|
Jeff (Junze) MaandOpenAI Codex
|
18c53727ce
|
[Bugfix][KV Connector] Fix DecodeBench DCP block selection (#54679)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-01 20:31:30 +00:00 |
|
|
|
7a977c0699
|
[ModelOpt] Redesign the LinearMethod classes using the generic QuantKey-driven method (#49381)
Signed-off-by: Juhi Mittal <juhim@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-01 16:28:56 -04:00 |
|
|
Kevin H. Luu
|
4bf06be985
|
[CI] Disable CUDA graphs for GLM PCP evals (#54745)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-09-01 20:24:46 +00:00 |
|
|
Zhewen Liandzhewenl
|
5cc32fbdfa
|
[Bugfix][KV Connector] Fix Mooncake physical-block transfer length (#54272)
Signed-off-by: zhewenl <zhewenl@users.noreply.github.com>
Co-authored-by: zhewenl <zhewenl@users.noreply.github.com>
|
2026-09-01 13:23:46 -07:00 |
|
|
|
7cb9a88f50
|
[Bugfix][Mooncake] Offload producer partial tails on request finish (#52832)
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-01 13:23:35 -07:00 |
|
|
Luyi XiaoandOpenAI Codex
|
aa71f9bcc4
|
[Bugfix] Log platform plugin detection failures (#52285)
Signed-off-by: Luyi Xiao <xiao.luy@northeastern.edu>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-01 19:11:52 +00:00 |
|
|
Divakar VermaandAndreas Karatzas
|
c0adee9231
|
[ROCm][CI] Add ROCm misc ops and env tests (#53279)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-01 19:03:37 +00:00 |
|