 Giancarlo DelfinandWoosuk Kwon
|
91945b6e4a
|
[Bug Fix][Model Runner V2][Spec Decode] Warmup & capture with different attention states for speculator prefill (#44253)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-03 13:32:40 -07:00 |
|
|
hoobnnandsfeng33
|
2b237c7a41
|
[Bugfix] Honor tool_choice="none" in Chat Completions streaming (#42752)
Signed-off-by: hoobnn <111053672+hoobnn@users.noreply.github.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-03 13:27:45 -07:00 |
|
|
Wentao Ye
|
dad95e34d8
|
[Feature] Support batch invariant rms norm with residual (#42453)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-03 15:22:01 -04:00 |
|
|
Luciano MartinsandLuciano Martins
|
a248b45d05
|
[Model] Add Gemma4 Unified (encoder-free) support (#44429)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-06-03 12:01:39 -07:00 |
|
|
linitra24
|
271328e256
|
[LoRA] Fix dedup for post-replacement module aliases (#44413)
Signed-off-by: bk-201 <joy25810@foxmail.com>
|
2026-06-03 18:23:23 +00:00 |
|
|
Wentao Ye
|
2b91012650
|
[Refactor] Remove dead code fp quant (#44122)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-03 14:22:23 -04:00 |
|
|
JartX
|
5b2a2beade
|
[ROCm][CI] Move Model Executor test step from MI250 to MI300 (gfx942) (#44370)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-06-03 12:23:51 -05:00 |
|
|
Chris LeonardandShengqi Chen
|
59d0236193
|
[10b/n] Migrate custom all-reduce, DeepSeek V4 fused MLA, MiniMax reduce-RMS, and MXFP8 MoE to libtorch stable ABI (#44365)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-06-04 00:29:46 +08:00 |
|
|
pschlan-amdandShengqi Chen
|
0a5cbf633e
|
Handle spinloop ext load failure gracefully (#43659)
Signed-off-by: Patrick Schlangen <pschlan@amd.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-06-03 16:09:52 +00:00 |
|
|
Willow Lopez
|
51e0c579b0
|
fix(config): validate max_num_scheduled_tokens >= 0 on all paths (#44207)
Signed-off-by: Oxygen56 <1391083091@qq.com>
|
2026-06-03 16:06:45 +00:00 |
|
|
|
0c6631f02a
|
[KVCache] Support Pluggable KVCacheSpec (#37505)
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-03 09:05:16 -07:00 |
|
|
Nicolò Lucchesi
|
df7252c343
|
[CI] Align PD tests to HMA on by default (#44174)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2026-06-04 00:04:30 +08:00 |
|
|
Jee Jee Li
|
4d1fd13613
|
[CI/Build] Fix LoRA testing (#44425)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-03 08:58:06 -07:00 |
|
|
Nick Hill
|
ec8d60bea8
|
[Model Runner V2] Use FlashInfer sampler (#42472)
|
2026-06-03 07:59:31 -07:00 |
|
|
|
27f1d34a23
|
[Frontend][Responses API] Move developer-to-system conversion into HF renderer (#43590)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: kdcyberdude <kdsingh.cyberdude@gmail.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
|
2026-06-03 14:52:24 +00:00 |
|
|
Flora Feng
|
e3e132d2dd
|
[Refactor] Suppress SyntaxWarning from ast.literal_eval in tool parsers (#44346)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-03 10:42:19 -04:00 |
|
|
|
e5232679a3
|
[XPU] Add XPU block-scaled W8A8 fp8 path (#39968)
Signed-off-by: Wu, Xiaochang <xiaochang.wu@intel.com>
Signed-off-by: Xiaochang Wu <xiaochang.wu@intel.com>
Co-authored-by: Yuxiang <yuxiang.liang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-03 20:16:19 +08:00 |
|
|
XunzhuoandBugen Zhao
|
309385a359
|
[Rust Frontend] Add /server_info to Rust frontend (#43942)
Signed-off-by: xunzhuo <xunzhuo@vllm-semantic-router.ai>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-03 04:30:47 -07:00 |
|
|
Varun Sundar Rabindranathandvarun sundar rabindranath
|
3d76f395e3
|
[SharedOffloadRegion] Align blocks to page-size (#43689)
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
|
2026-06-03 14:25:57 +03:00 |
|
|
Li, Jiang
|
823d271c0d
|
[Attention][CPU] Standardize kv layout to blocks first (#44393)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-06-03 19:03:09 +08:00 |
|
|
Andy Lo
|
95b1615ec9
|
[Perf] Improve multimodal item handling from O(n) to O(log n) per step (#44212)
Signed-off-by: Andy Lo <andy@mistral.ai>
|
2026-06-03 11:00:26 +00:00 |
|
|
|
1fa9ea09f6
|
[Perf] Triton fast path for small CPU→GPU swap_blocks_batch in the offloading connector (#42212)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-03 13:38:17 +03:00 |
|
|
Yan MaandKunshang Ji
|
02564b4de0
|
[XPU]fallback to TRITON_ATTN for vit attn on xpu when use float32 dtype (#43759)
Signed-off-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-03 03:20:21 -07:00 |
|
|
Flora Feng
|
209709a8c1
|
[Bugfix] Fix unstreamed tool call args dropped in Responses API streaming (#44348)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-03 03:19:08 -07:00 |
|
|
Wei Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ace95c9cf8
|
[Bugfix] Update TrtLLM MoE routing methods (#44347)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-03 02:56:43 -07:00 |
|
|
Shanshan Shen
|
0e2b13103b
|
[Doc] Update ViT CUDA graph interfaces (#44388)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-06-03 01:20:59 -07:00 |
|
|
Bugen Zhao
|
449be4f934
|
[Rust Frontend] Fix several hf chat template rendering issues (#44311)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-03 01:04:43 -07:00 |
|
|
XunzhuoandBugen Zhao
|
6550ff12f2
|
[Rust Frontend] Add dynamic LoRA endpoints (#43778)
Signed-off-by: xunzhuo <xunzhuo@vllm-semantic-router.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-03 07:55:29 +00:00 |
|
|
|
4aaed4ca22
|
[Rust Frontend] Add server router extension hook (#43774)
Signed-off-by: NolanHo <kujyo.eia.serias@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-03 07:45:31 +00:00 |
|
|
Varun Sundar Rabindranathandvarun sundar rabindranath
|
7268457999
|
[KV Offloading] Enable HMA models for Tiering Offloading (#44287)
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
|
2026-06-03 10:03:00 +03:00 |
|
|
|
9af53a3c13
|
[Perf] Add tuned selective_state_update configs for H200 and RTX PRO … (#44251)
Signed-off-by: Majid Taheri Andani <tahemaji@amazon.com>
Co-authored-by: Majid Taheri Andani <tahemaji@amazon.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
|
2026-06-02 23:59:01 -07:00 |
|
|
Andreas Karatzas
|
87954eb50e
|
[ROCm][CI] Optimize ROCm Docker build: registry cache, DeepEP, and ci-bake script (#36949)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-02 23:43:07 -07:00 |
|
|
Charlie Fu
|
71df063c49
|
Enable perf_token_group_quant/_C_stable_libtorch for ROCm (#42758)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-06-02 23:23:28 -07:00 |
|
|
Albert Cheng
|
e0081ef8cf
|
[Benchmark] Enable reasoning-model (thinking) benchmarking via --chat-template-kwargs for client-rendered datasets (#44244)
Signed-off-by: Albert Cheng <albertching0112@gmail.com>
|
2026-06-02 22:49:51 -07:00 |
|
|
William Romandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
f0204358d9
|
[Bugfix] fix crash in postprocess for null tool args (#43862)
Signed-off-by: William-Rom <william.rom@intility.no>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-02 22:17:26 -07:00 |
|
|
Willow Lopez
|
597bc15936
|
fix: resolve CUTLASS fmin compatibility for DeepSeek-V4 init (#44236)
Signed-off-by: Willow Lopez <100782273+Oxygen56@users.noreply.github.com>
|
2026-06-03 01:07:10 -04:00 |
|
|
Rotem Shavitt
|
3f0a91bb96
|
Nit Changes in Tiered KV Offload (#44293)
Signed-off-by: Rotem Shavitt <rshavitt@gmail.com>
|
2026-06-02 21:53:21 -07:00 |
|
|
Flora Feng
|
e67063826b
|
[CI] Add missing vllm/parser/ CI trigger and fix test_parse.py (#44352)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-02 21:05:19 -07:00 |
|
|
Andreas Karatzas
|
53b88d1dfc
|
[CI] Reject out-of-vocabulary before they reach the GPU logprob path (#44042)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-02 22:27:52 -05:00 |
|
|
JartX
|
7b476c8f14
|
[ROCm][CI] Skip fp8 reload tests on gfx90a (MI250) (#44369)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-06-02 22:27:14 -05:00 |
|
|
JartX
|
4454a18695
|
[ROCm][CI] Fix stale wvSplitK GEMM fallback test for N=5 (#44368)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-06-02 22:00:25 -05:00 |
|
|
wangxiyuanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
02a01496fc
|
[Platform] Add is_cumem_allocator_available (#43838)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-03 10:54:50 +08:00 |
|
|
Kevin H. Luu
|
27a93cd426
|
[docker] Stop using extra-index-url for flashinfer-jit-cache (#44366)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-06-02 18:58:22 -07:00 |
|
|
Wei Zhao
|
969aec4bc8
|
[Bugfix] Fix Deepseek v4 non-mega-moe model init error (#44356)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-02 18:26:30 -07:00 |
|
|
Jongseok ParkandNick Hill
|
ca17b6b17d
|
[Perf] Apply single-pass min_larger finding and binary search in Triton Top-p path. (#42191)
Signed-off-by: js_park <cakeng@naver.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-06-02 17:57:26 -07:00 |
|
|
Woosuk Kwon
|
b254e0456c
|
[DSV4] Minor cleanup for DeepseekV4MegaMoEExperts (#44367)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-02 17:54:27 -07:00 |
|
|
Daoyuan Li
|
bd98e97557
|
[Misc] Remove dead VLLM_RPC_TIMEOUT env var and fix profiling doc that references it (#44128)
Signed-off-by: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com>
|
2026-06-03 00:22:10 +00:00 |
|
|
Junhao ShenandVadim Gimpelson
|
a4ac746405
|
[MoE/b12x] Accept W4A16 (kNvfp4Static, None) in FlashInferB12xExperts supports check (#43332)
Signed-off-by: Junhao Shen <junshen@nvidia.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-06-02 15:20:37 -07:00 |
|
|
Vadim GimpelsonandJee Jee Li
|
8b3b71ee9d
|
[CI/Build] Bump flashinfer to v0.6.12 (#44036)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-02 15:19:05 -07:00 |
|
|
Siddharth Bedekar
|
0917a009d3
|
Fix sparse NCCL weight transfer test construction (#44345)
Signed-off-by: Siddharth Bedekar <bedeksid@gmail.com>
|
2026-06-02 21:51:21 +00:00 |
|