 haosdentandWentao Ye
|
5ea76fa89a
|
[CI] Fix test_lora_with_spec_decode on V2 model runner (#43314)
Signed-off-by: haosdent <haosdent@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-22 14:24:18 +08:00 |
|
|
tc-mb
|
fa1ff88b31
|
[Model] Fix MiniCPM-V 4.6 vit_merger qkv weight loading (#43213)
Signed-off-by: tc-mb <tianchi_cai@icloud.com>
|
2026-05-21 22:44:06 -07:00 |
|
|
Furkan F
|
e746a2eebf
|
[Model] Use AutoWeightsLoader for Voyage (#42972)
Signed-off-by: Furkan Fidan <dev@yufufi.com>
|
2026-05-22 05:28:23 +00:00 |
|
|
Xiaochang WuandKunshang Ji
|
8c8b1825eb
|
[XPU] Enable multiple key kernels for sparse attention (#37888)
Signed-off-by: Xiaochang Wu <xiaochang.wu@intel.com>
Signed-off-by: Wu, Xiaochang <xiaochang.wu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-22 12:02:51 +08:00 |
|
|
qizixiandClaude
|
18a27cc9a3
|
[Bugfix] Make CuMemAllocator free callback stream-aware (#43020)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-22 03:36:22 +00:00 |
|
|
|
0ddd7dd656
|
[Frontend] DP Supervisor (#40841)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: robertgshaw2-redhat <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 20:33:16 -07:00 |
|
|
ruizhangandRui Zhang
|
60af5c16ee
|
[Frontend] Add truncation side to OpenAI endpoints (#43260)
Signed-off-by: Rui Zhang <rza21.bc@gmail.com>
Signed-off-by: Rui Zhang <rui.zhang@globalrelay.net>
Co-authored-by: Rui Zhang <rui.zhang@globalrelay.net>
|
2026-05-21 20:32:31 -07:00 |
|
|
Simon Danielsson
|
86ccef7d44
|
[ROCm] Add XGMI backend for MoRI Connector (#41753)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-05-22 03:06:40 +00:00 |
|
|
Chengze FanandLu Fang
|
2998a047aa
|
[Bugfix] Fix DSV4 Base model swiglu limit issue in FP8 path (#42855)
Signed-off-by: Chengze Fan <chengze@meta.com>
Signed-off-by: Chengze Fan <fancz2002@gmail.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
|
2026-05-21 19:43:01 -07:00 |
|
|
Lanze Liu
|
39d5fa96a7
|
[Bugfix] Zero stale is_prefilling in padded CUDA graph rows for Mamba (#41873)
Signed-off-by: Lanze Liu <lanzetech@gmail.com>
|
2026-05-21 15:42:42 -07:00 |
|
|
Nick Hill
|
565b745ec5
|
[BugFix] Use correct logprobs for logprob_token_ids (#43125)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 15:42:20 -07:00 |
|
|
|
e26e1f0928
|
[Feature] Add --cpu-distributed-timeout-seconds CLI Option for CPU Process Group Timeout (#42968)
Signed-off-by: fangyuchu <fangyuchu@qq.com>
Signed-off-by: zWaNg3 <389750525@qq.com>
Co-authored-by: zWaNg3 <389750525@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-21 15:42:07 -07:00 |
|
|
Nick Hill
|
0f66623b0d
|
[Frontend] Rework fastokens integration (#43168)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 15:36:58 -07:00 |
|
|
|
17b69828a0
|
[Core] Add native ModelExpress load format (#43105)
Signed-off-by: Zheng Luo <zheluo@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-05-21 16:05:01 -04:00 |
|
|
Wentao Ye
|
b29cbf0652
|
[Perf] zeros -> empty to remove additional fill (#42988)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-21 16:00:29 -04:00 |
|
|
Michael Goin
|
9b54e50e2c
|
[Deprecation] Mark env vars covered by --moe-backend / --linear-backend (#43148)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
|
2026-05-21 12:51:12 -07:00 |
|
|
|
1c78f76c29
|
[Bugfix] Add early validation to reject incompatible runner types for embedding models (#43079)
Signed-off-by: anish <anishesg@users.noreply.github.com>
Signed-off-by: Your Name <ak8686@princeton.edu>
Signed-off-by: anish <145943060+anishesg@users.noreply.github.com>
Co-authored-by: anish <anishesg@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-21 11:07:46 -04:00 |
|
|
haosdent
|
9b9d5dbaab
|
[CI] Fix CPU tests failing on tl.exp2 import (#43311)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-05-21 14:28:34 +00:00 |
|
|
Francesco Fuscoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
b730c46352
|
[Perf] [Hybrid] Fused Triton kernel for GPU-side Mamba state postprocessing (#40172)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-21 04:50:54 -07:00 |
|
|
|
c68c55d43e
|
[CPU][RISC-V] Add VLEN=256 support to RVV attention kernels (#42943)
Signed-off-by: velonica0 <like@mail.nankai.edu.cn>
Signed-off-by: velonica0 <47554626+velonica0@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-21 04:50:49 -07:00 |
|
|
Wentao YeandIsotr0py
|
68e07d5916
|
[Bug] Fix ci issue assert output_size is not None AssertionError (#43261)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-05-21 16:58:09 +08:00 |
|
|
zhangxin81
|
edafea3555
|
Fix FlashInfer TRTLLM NvFP4 monolithic MoE routing (#43223)
Signed-off-by: zhangxin81 <115389973+zhangxin81@users.noreply.github.com>
|
2026-05-21 01:17:12 -07:00 |
|
|
zexplorerhjandzexplorerhj
|
b719b1635b
|
Update KDA chunk prefill decay to use exp2 semantics (#43195)
Signed-off-by: zexplorerhj <19794632+zexplorerhj@users.noreply.github.com>
Co-authored-by: zexplorerhj <19794632+zexplorerhj@users.noreply.github.com>
|
2026-05-21 01:16:27 -07:00 |
|
|
haosdent
|
a950e9447e
|
[CI] De-flake test_models for bigscience/bloom-560m (#43197)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-05-21 06:30:14 +00:00 |
|
|
|
050611a3dd
|
[Bugfix] Fix glm4_moe_tool_parser._is_string_type for /v1/responses FunctionTool format (#39601)
Signed-off-by: Yiyang Liu <37043548+ianliuy@users.noreply.github.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-20 22:58:59 -07:00 |
|
|
yzong-rh
|
905b97adfa
|
[Benchmark] Add num-warmup to vllm bench throughput (#43245)
Signed-off-by: Yifan Zong <yzong@redhat.com>
|
2026-05-21 05:13:15 +00:00 |
|
|
Daoyuan Li
|
a6682d1d25
|
[Bugfix] Warn when renderer_num_workers has no effect on offline LLM (#42905)
Signed-off-by: Daoyuan Li <94409450+DaoyuanLi2816@users.noreply.github.com>
|
2026-05-20 21:35:08 -07:00 |
|
|
Nick HillandBugen Zhao
|
f2ace1d57d
|
[Frontend][RFC] Rust front-end integration (#40848)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-05-21 12:24:48 +08:00 |
|
|
|
d97ba29fdc
|
[ToolParser][Bugfix] Re-land: Fix anyOf/oneOf/$ref type resolution in Qwen3CoderToolParser (#37831) (#38973)
Signed-off-by: AAISSJ <maze0717@g.skku.edu>
Signed-off-by: <>
Signed-off-by: sejung-son <sejung.son@nhn.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: 세덩 <saison@sedeong-ui-MacBookAir.local>
Co-authored-by: sejung-son <sejung.son@nhn.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-21 12:24:08 +08:00 |
|
|
Flora Feng
|
6441cf4a44
|
[Refactor] Use shared coerce_to_schema_type in Seed-OSS tool parser (#43140)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-20 21:24:06 -07:00 |
|
|
Ben Browningandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
346cf163a1
|
[Frontend] Normalize reasoning_content to reasoning for client compatibility (#42664)
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-20 21:23:47 -07:00 |
|
|
Luciano MartinsandLuciano Martins
|
2b75a73b8e
|
[Perf][Gemma4] Batch vision encoder calls for image and video processing (#43169)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-05-20 21:22:06 -07:00 |
|
|
|
e45df8c3f7
|
[Bugfix] Fix Qwen3.5 GatedDeltaNet in_proj_ba Marlin failure at TP>=2 (#36329)
Signed-off-by: Adi McM Sonus Flow <biuro@sonusflow.pl>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-20 21:22:01 -07:00 |
|
|
Jee Jee Li
|
ee05e8137e
|
[Minor] Bigger overlap for FI AR (#43103)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-05-20 21:20:57 -07:00 |
|
|
Wentao YeandNick Hill
|
9640970de2
|
[Model Runner V2] Fix lora Triton Error [CUDA]: device-side assert triggered (#43139)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 01:00:30 +00:00 |
|
|
akii96
|
bde560ed6e
|
[ROCm] Add QuickReduce min-size override and codec threshold (#41675)
Signed-off-by: <>
|
2026-05-20 17:46:51 -05:00 |
|
|
Michael Goin
|
5774aad9c5
|
[Perf][gpt-oss] Downgrade triton_kernels to v3.5.1 (#43135)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-05-20 14:13:12 -07:00 |
|
|
Flora Feng
|
2a43b407c5
|
[Bugfix][CI] Add missing import of pad_nvfp4_activation_for_cutlass in flashinfer (#43237)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-20 11:59:12 -07:00 |
|
|
Wentao YeandMatthew Bonanni
|
53ff50fcd3
|
[Perf] Optimize CutlassFP8ScaledMMLinearKernel when padding needed by pre-weight processing, 13.5% TTFT improvement (#42651)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-05-20 11:57:42 -07:00 |
|
|
meena-at-workandClaude Sonnet 4.6
|
363fc84407
|
Integrate flashinfer b12x MoE and FP4 GEMM kernels for SM120/121 (#40082)
Signed-off-by: Meenakshi Venkataraman <meenakshiv@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-05-20 17:21:11 +00:00 |
|
|
Aaron HaoandIsotr0py
|
2d6b3489b9
|
[R3] Add routed experts to openai entrypoint (#38939)
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-05-20 09:07:59 -07:00 |
|
|
Vadim Gimpelson
|
9c78c99995
|
[MISC] Fix symm_mem cap-equal gate; log AR backend selection (#42993)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-05-20 08:50:24 -07:00 |
|
|
Flora Feng
|
a10d69116c
|
[Bugfix] Use shared coerce_to_schema_type in DeepSeekV32 tool parser (#43019)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-20 10:21:00 -04:00 |
|
|
rishitdholakia13andCursor
|
ded871201a
|
[Bug][Structured Outputs] Fix bug that leads to unconstrained generations with structural tags (#42452)
Signed-off-by: rishitdholakia13 <rishit+github@cohere.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-20 07:08:58 -07:00 |
|
|
Dipika Sikka
|
df84fb07a6
|
Remove additional dead code as a follow-up to #42889 (#43144)
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
|
2026-05-20 10:01:45 -04:00 |
|
|
Benjamin Chislett
|
0a508743d4
|
[Spec Decode] Support non-MTP speculation for NemotronH (#43130)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-05-20 09:15:52 -04:00 |
|
|
Kebe
|
19cf334207
|
[Feature] Support manually enabling the cumem allocator (#33648)
Signed-off-by: Kebe <mail@kebe7jun.com>
|
2026-05-20 08:58:30 -04:00 |
|
|
halleriteandClaude Opus 4.7
|
cb600d1cdb
|
[Frontend] Forward X-data-parallel-rank header on /inference/v1/generate (#42330)
Signed-off-by: hallerite <git@hallerite.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-20 08:58:46 +00:00 |
|
|
Artem Perevedentsev
|
1cb224430b
|
[GDN] Enable FI Blackwell GDN prefill kernel (#40717)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-05-20 01:46:55 -07:00 |
|
|
|
07aeaf9d4d
|
[6/n] Migrate activation kernels, gptq, gguf, non cutlass w8a8 to libtorch stable ABI (continued) (#42663)
Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Co-authored-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-05-20 00:18:12 -07:00 |
|