Commit Graph
20752 Commits
Author SHA1 Message Date
Kevin H. Luu f5711fa138 [CI] Shard LoRA TP distributed tests (#52350)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-02 01:16:44 -07:00
Chauncey b2558f8da3 [Bugfix] Fix launch render hanging on shutdown (#54913)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-09-02 08:15:35 +00:00
Zeyu YangandYikun Jiang c23e15be9f [CI][Fix] Resolved the Ascend NPU test build image fail and add file dependencies (#50504)
Signed-off-by: yangzeyu <yangzeyu7@huawei.com>
Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
2026-09-02 08:14:00 +00:00
Kevin H. Luu 878ec4bfee [CI] Shard entrypoints API-server tests (#52344)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-02 01:13:38 -07:00
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
Itay EtelisItay EtelisOr Ozerimergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
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
Kevin H. Luu 3976eada8b [CI] Use PR head label for Buildkite branch to avoid main collision (#54895)
Signed-off-by: khluu <khluu000@gmail.com>
2026-09-01 23:09:50 -07:00
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
Giuseppe GrossiandAndreas Karatzas 56b5495377 [ROCm][AMD][Installation] Add mooncake build to rocm base image (#52650)
Signed-off-by: Giuseppe Grossi <ggrossi@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-02 00:14:58 -05:00
xiangdong ad76610c40 [XPU][CI] Move heavy jobs to nightly test in Intel GPU CI (#54863)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
2026-09-02 13:11:01 +08:00
Andreas KaratzasandOpenAI Codex 73029d4244 [CI][ROCm] Calibrate AMD test timeouts from nightly runtimes (#54695)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-01 23:53:12 -05:00
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
Kevin H. Luu 05201d8ecf [CI] Shard basic model initialization tests (#54753)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-02 04:31:57 +00:00
Gabriel WuandKimi Code 396c5a5632 [Bugfix] Lazy-import FlashInfer PCIe IPC all-reduce in kernel_warmup (#54869)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
2026-09-02 04:31:03 +00:00
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
Isotr0py 1d8d7a3965 [Bugfix] Fix RoPE construction for deepseek-v4 sparse SWA layers (#54815)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
2026-09-01 20:48:50 -07:00
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> a566ea7e8f [Perf] Avoid more h2d copies from non-pinned tensors (#54660)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-01 20:37:09 -07:00
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
Divakar VermaandAndreas Karatzas dbf1a044ea [Bugfix] Fix ColQwen3.5 pooler projector initialization (#54847)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-02 10:35:43 +08:00
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
Bugen ZhaoandCodex 80389cfedd [CI/Build] Gate PR title check on ready PRs & use slim runners (#54827)
Co-authored-by: Codex <codex@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-09-01 23:12:00 +00:00
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
Kevin H. Luu 3b6c0bdae9 [CI] Shard long kernel test groups (#54754)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-01 15:58:27 -07:00
Kevin H. Luu 96031b8623 [CI] Shard distributed model jobs above the 24h P90 threshold (#54752)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-01 15:32:11 -07:00
Kevin H. Luu e90b608c42 [CI] Split nightly MTP acceptance tests (#52353)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-01 15:29:33 -07:00
Bugen Zhao b911fe85c4 [Rust Frontend] Attribute decoded text to tokens (#52910)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-09-01 22:25:31 +00:00
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
Micah Williamson ce6a283c09 [Bugfix] Restore weight_dtype in QuarkW8A8Fp8MoEMethod to fix GPT-OSS FP8 MoE weight loading (#54824)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2026-09-01 16:08:11 -05:00
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
Andrey Talman 16f16876fd [CI] Read the CRCR report token from a Buildkite secret (#54605)
Signed-off-by: Andrey Talman <atalman@fb.com>
2026-09-01 20:29:23 +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
Isotr0py dc5cf437cf [Rust Frontend] Enable Qwen4-exp multimodal support (#54813) 2026-09-01 20:23:55 +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
Alberto MassiddaandAlberto Massidda 55178f2d09 [Bugfix][Profiler] Fix API server crash on double /stop_profile (#51678)
Signed-off-by: Alberto Massidda <amassidda@nvidia.com>
Co-authored-by: Alberto Massidda <amassidda@nvidia.com>
2026-09-01 13:05:04 -07:00
stefankoncarevic 73723b707f [ROCm][MoE] Fix gfx950 block scale swizzle for AITER Triton MXFP4 W4A16 (#54773)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
2026-09-01 19:48:45 +00:00
Bugen Zhao 3439bad37e [Rust Frontend] Bound recursive argument parsers (#54303)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-09-01 12:45:50 -07:00
Julien Debache ab54f5bd83 [Chore] Remove redundant _pack_topk_ids_weights_kernel in TrtLLM NvFP4 MoE (#46872)
Signed-off-by: jdebache <jdebache@nvidia.com>
2026-09-01 15:30:11 -04:00
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