|
0106c8abce
|
[CI] Shard FP8 MoE kernels and L4 Humming eval automatically (#61831)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-27 17:54:04 -07:00 |
|
|
Woosuk KwonandCodex
|
a91b939bfb
|
[Bugfix][Bench] Support Muse balanced routing (#63872)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-27 17:50:19 -07:00 |
|
|
yzong-rh
|
c4f2bb4abb
|
[Bugfix][Spec Decode] Preserve grammar-invalid drafts for rejection sampling (#61557)
Signed-off-by: Yifan Zong <yzong@redhat.com>
|
2026-10-27 23:09:32 +02:00 |
|
|
Roberto L. Castroandvllm-agent
|
a2ad4b74b9
|
[Perf] Enable DeepGEMM sparse MQA logits on the FP8 indexer cache, DSv4.1 (#62011)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 19:25:19 +00:00 |
|
|
GuorongYeandgrYe99
|
bfa2a43345
|
[CI] Fix stale NVFP4 decode test selector on DGX Spark (#64107)
Signed-off-by: grYe99 <guorongye99@gmail.com>
Co-authored-by: grYe99 <guorongye99@gmail.com>
|
2026-10-27 12:00:49 -07:00 |
|
|
|
b29caba14e
|
[CI] Shard draft decoding, Qwen eval and scheduling automatically (#61832)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-27 04:21:50 -07:00 |
|
|
|
de58886274
|
[CI] Move B200 Kernels and MoE Refactor evals from manual to automatic shards (#62120)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 03:57:47 -07:00 |
|
|
Thang NguyenandClaude Opus 5.5
|
eb5e8d1cc8
|
[CI] Move L4 Distributed Models and LoRA TP and their AMD mirrors from fixed to automatic shards (#62537)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-27 03:49:07 -07:00 |
|
|
|
659defd662
|
[CI] Shard the AMD mirrors of Basic Models (Other) and PCP automatically (#61904)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 03:47:24 -07:00 |
|
|
Thang NguyenandClaude Opus 5.5
|
f62e80ff04
|
[CI] Enroll 4 steps and 2 AMD mirrors in automatic sharding (#63907)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-27 03:44:27 -07:00 |
|
|
NVShreyasandThien Tran
|
8e26dec5f5
|
[Kernel][MiniMax-M3] Add Triton query-tiled sparse prefill tuned on Hopper (#57420)
Signed-off-by: Shreyas Misra <shreyasm@nvidia.com>
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-10-27 16:26:03 +07:00 |
|
|
|
0076619a94
|
[Perf][Kernel] Add a CuteDSL BF16x3 router GEMM for fp32 router weights on Hopper (#61903)
Signed-off-by: Chen Cheng <85005591+ischencheng@users.noreply.github.com>
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 02:16:44 -07:00 |
|
|
|
6fe3d447ac
|
[CI][AMD] Mirror ReplaySSM, MiniMax-M3 attention kernels and Kimi K3 prefix cache on MI355 (#62141)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 23:13:38 -05:00 |
|
|
|
3d81a510f9
|
[ROCm] DeepSeek-V4-Pro PD Disaggregation through MORI IO KV Connector on AMD GPUs (#48989)
Signed-off-by: Tej Kiran <kiran.tej@amd.com>
Co-authored-by: Tej Kiran <kiran.tej@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-10-27 11:08:13 +08:00 |
|
|
|
967c39f89e
|
[CI] List one test path per line in Buildkite pytest commands to avoid merge conflicts (#63408)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 16:15:29 -07:00 |
|
|
Oxana KorzhandClaude Opus 5.5
|
537a79f0fc
|
[CI] Add missing && in the Multi-Modal Models (Standard) 3 command (#63422)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-26 14:57:18 -07:00 |
|
|
|
9e3db48873
|
[MoE] Add locality-domain allocation for FlashInfer CuTeDSL NVFP4 (#61685)
Signed-off-by: Qidong Su <qidongs@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Bolin Sun <bolins@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-10-26 14:37:01 -04:00 |
|
|
djramic
|
df8b5d3781
|
[ROCm][CI] Raise MI300 Core Operation Kernels timeout to 90 min (#63760)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-10-26 10:59:23 -05:00 |
|
|
|
ffcabb8c7a
|
[docker] add vllm-openai-efa target (#58768)
Signed-off-by: Sunita Nadampalli <nadampal@amazon.com>
Co-authored-by: Erez Zarum <erezz@amazon.com>
Co-authored-by: Sean Westfall <sean.westfall@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-26 03:51:30 -07:00 |
|
|
JartXandtjtanaa
|
00b6c4c565
|
[ROCm] Octave KV (ROCM_OCTAVE): native 3-bit KV cache backend for AMD GPUs (#59774)
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-10-26 12:35:00 +08:00 |
|
|
|
cd9aa5b5ee
|
[Bugfix][Platform] Keep PIN_MEMORY eager; avoid resolving platform during import vllm (#63601)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 03:09:30 +00:00 |
|
|
Woosuk KwonandCodex
|
a7407ab445
|
[Benchmark] Add steady-state PP support to bench forward (#63616)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-25 16:55:29 -07:00 |
|
|
Pablo LlopisandNicolò Lucchesi
|
2c880f1e68
|
[Bugfix] Preserve FP8 indexer WK pairs across load_weights calls (#59223)
Signed-off-by: Pablo Llopis <pablo.llopis@epfl.ch>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
|
2026-10-25 19:42:48 +00:00 |
|
|
Kevin H. Luu
|
f8c12c212a
|
[CI] Disable jobs with unpinned runtime installs (#63609)
Signed-off-by: khluu <khluu000@gmail.com>
|
2026-10-25 12:40:35 -07:00 |
|
|
Kevin H. Luu
|
9d48c8ab95
|
[CI] Disable jobs with unlocked transitive dependencies (#63608)
Signed-off-by: khluu <khluu000@gmail.com>
|
2026-10-25 12:30:06 -07:00 |
|
|
John CalderonandArtem Perevedentsev
|
fa2881ed19
|
[CI][Benchmarks] Fix attention smoke test backend names and failure exit status (#63177)
Signed-off-by: John Calderon <jcalderon@nvidia.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-10-25 17:31:31 +02:00 |
|
|
Shantanu AcharyaandRoger Wang
|
75fc05a53a
|
[Model] Add Dory support (#60149)
Signed-off-by: Shantanu Acharya <shantanua@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-10-25 11:13:22 +00:00 |
|
|
|
5f63ea461c
|
[Bugfix][Quantization][Spec Decode] Load ModelOpt mixed-precision DFlash and DSpark drafts (#63001)
Signed-off-by: Sandeep Agrawal <sandeepa@nvidia.com>
Co-authored-by: Kotaro Yamamoto <kyamamoto@nvidia.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-24 08:28:36 -04:00 |
|
|
|
139feb4534
|
[ROCm][Perf][DSv4] Standalone mono decode layer for DeepSeek-V4-Pro on MI355X (#61482)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-24 20:00:39 +08:00 |
|
|
TJianandClaude Opus 5.5
|
2aa7269a83
|
[Bugfix][ROCm][MoRIIO] Release every prefill rank a READ holds (#62473)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-24 11:53:20 +00:00 |
|
|
|
debcf22843
|
[CI][ROCm] Export kernel source maps for CI selection (#59100)
Signed-off-by: Andreas Karatzas <andreas.karatzas@protonmail.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Andreas Karatzas <AndreasKaratzas@users.noreply.github.com>
|
2026-10-23 18:05:23 -07:00 |
|
|
Kevin H. Luu
|
6fd0e701fd
|
[CI] Remove redundant Ubuntu 24.04 release variant (#63413)
Signed-off-by: khluu <khluu000@gmail.com>
|
2026-10-23 14:37:15 -07:00 |
|
|
Divakar Vermaandvllm-agent
|
be03d19750
|
[CI][ROCm][MoE] Add MXFP4 SWIGLUOAI_UNINTERLEAVE/SITU test coverage on MI355 (#62907)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 15:57:57 -05:00 |
|
|
Andreas KaratzasandClaude
|
bc3afc4096
|
[CI][ROCm] Fail the AITER nightly overlay on wheels ci_base cannot load (#63242)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-23 15:55:44 -05:00 |
|
|
|
b1c66e5545
|
[ROCm][Model] Muse Spark: share one RoPE cache sized by max_model_len (#62757)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 14:39:46 -05:00 |
|
|
djramic
|
224b2f54f1
|
[ROCm][CI] Move NFS-affected MI300 test groups to MI355 (#62934)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-10-23 13:45:27 -05:00 |
|
|
Andreas KaratzasandClaude
|
c0a41721c7
|
[CI][ROCm] Raise the MI355 MiniMax M3 MonoKernel timeout to 45 minutes (#63269)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-23 15:34:38 +00:00 |
|
|
|
c569393ed2
|
[CI][Rust Frontend] Run more Python server tests against the Rust frontend (#63320)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 22:14:07 +08:00 |
|
|
Fanli Linandvllm-agent
|
4bceda5dbf
|
[XPU][CI] Run prefix-caching tests for GDN, Mamba and pooling models on XPU (#62683)
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 21:41:49 +08:00 |
|
|
|
5c465dda9d
|
[Rust Frontend] Report every invalid logit_bias key like Python (#63313)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 18:53:52 +08:00 |
|
|
Mritunjay Kumar Sharma
|
14b4576e70
|
[Security][CI/Build] Bump uv to 0.13.4 in CI scripts for eMudhra CA distrust (#63191)
Signed-off-by: Mritunjay Sharma <mritunjaysharma394@gmail.com>
|
2026-10-23 05:15:04 +00:00 |
|
|
|
3dbf2b6c0c
|
[Bugfix][ROCm] Muse Spark: apply output multiplier and softcap in compute_logits_local (#62756)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-10-22 23:34:47 -05:00 |
|
|
Li, Jiang
|
284c0317c4
|
[CPU] Add GELU-tanh MoE, FP8 checkpoint support and Gemma-4 INT8 TP=4 padding (#62016)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-10-23 11:39:37 +08:00 |
|
|
lishuoshuo-amdandShanshan Shen
|
f120f1dbf2
|
[Bugfix][ROCm][MiniMax-M3] Reject IndexCache overrides that miss text_config (#63082)
Signed-off-by: lishuoshuo-amd <shuoli@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-23 10:34:20 +08:00 |
|
|
Yan Maandvllm-agent
|
d5d8ccaae6
|
[XPU] temporarily ignore test_cumem.py::test_basic_cumem (#63084)
Signed-off-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 09:24:25 +08:00 |
|
|
|
432b1003f8
|
[Bugfix] Defer MRV2 Triton validation to worker startup (#62576)
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-22 17:51:11 -07:00 |
|
|
Woosuk KwonandClaude Opus 5.5
|
899a1689e2
|
[Model] Add Recursive Flint (#62938)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-22 14:56:35 -07:00 |
|
|
|
ce9467b757
|
[Core] Add XPress speculative decoding method (#54448)
Signed-off-by: Zheng Wang <zhengw10@illinois.edu>
Signed-off-by: Ubuntu <ubuntu@ip-172-31-27-124.us-west-2.compute.internal>
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-22 17:04:54 -04:00 |
|
|
|
e7bb7e2f20
|
[bug-fix] Fix KV block leak with fault tolerance enabled in P/D disaggregation (#56430)
Signed-off-by: tiankaijin <tiankaijin1@h-partners.com>
Signed-off-by: tiankaijin <1669619752@qq.com>
Co-authored-by: tiankaijin <tiankaijin1@h-partners.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Pioneer-Weirdo <80094616+Pioneer-Weirdo@users.noreply.github.com>
|
2026-10-22 18:14:25 +00:00 |
|
|
+4
|
6ab6bff1b6
|
[Model][ROCm] Add Muse Spark Open support on ROCm (#62622)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Jiahan Chang (Cyrus) <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com>
Co-authored-by: qizixi <22851944+zixi-qi@users.noreply.github.com>
Co-authored-by: haic0 <149741444+haic0@users.noreply.github.com>
Co-authored-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: Shangdi Yu <yushangdi123@gmail.com>
Co-authored-by: JohnQinAMD <yanyuan.qin@amd.com>
Co-authored-by: Duncan Moss <6038874+djmmoss@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-10-22 17:00:09 +08:00 |
|