 Sherif Waly
|
4d95f222e6
|
[Feature][Core] Enable best-effort NUMA binding by default (#61258)
|
2026-10-27 22:36:02 +01:00 |
|
|
|
70cb50dab2
|
[Feature][HiSparse] Add a platform backend for device operations (#62592)
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-10-27 21:18:40 +00:00 |
|
|
|
e1e77a279d
|
[Bugfix] Bound prefix cache reuse by the first requested prompt score (#60960)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 19:26:07 +00:00 |
|
|
Woosuk KwonandCodex
|
e3ba8d00db
|
[Bugfix][Bench] Handle packed hybrid KV and speculative recurrent state (#63873)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-27 09:04:59 -07:00 |
|
|
Isotr0pyandvllm-agent
|
a9b727a612
|
[UX] Remove --hf-overrides necessity for Qwen3-ASR-ForceAligner (#63274)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 23:20:03 +08:00 |
|
|
|
a5b257a34b
|
[Docs][KV Connector] Document standalone Mooncake EGM deployment (#63064)
Signed-off-by: wugou.cyf <wugou.cyf@antfin.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: wugou.cyf <wugou.cyf@antfin.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-27 09:34:36 +00:00 |
|
|
Schwinn Saereesitthipitakandvllm-agent
|
05a303fdc8
|
[Core][Frontend] Process checkpoint lifecycle with HTTP prepare/status/resume (#62570)
Signed-off-by: Schwinn Saereesitthipitak <schwinns@nvidia.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-27 08:02:44 +00:00 |
|
|
|
4f140a23de
|
[Bugfix] Initialize valid ModelOpt NVFP4 MoE dummy scales (#63698)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 09:31:41 -07:00 |
|
|
Aaron HaoandClaude Opus 5.5
|
50a184f435
|
[RL] Declare weight ownership and layout on ParamMeta (#63256)
Signed-off-by: Aaron Hao <aaronhao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-26 23:42:30 +08:00 |
|
|
Li Wangandwangli
|
0abec7309e
|
[Model] Add native support for Lfm2BidirectionalModel (#62201)
Signed-off-by: wangli <wangli858794774@gmil.com>
Co-authored-by: wangli <wangli858794774@gmil.com>
|
2026-10-26 15:31:39 +00:00 |
|
|
|
e113018f50
|
[Bugfix][KV Offload] Preserve running request prefixes across LRU store batches (#61050)
Signed-off-by: Jack Brown <rnk.liulw@gmail.com>
Co-authored-by: Jack Brown <rnk.liulw@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 17:30:22 +02:00 |
|
|
Tony LinandNicolò Lucchesi
|
74340c7300
|
[docs] correct NIXL hybrid SSM heterogeneous TP support (#63036)
Signed-off-by: Tony Lin <tony.lin@intel.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
|
2026-10-26 14:16:11 +00:00 |
|
|
Amir FriedmanandClaude Opus 5
|
5b06b5f8e9
|
[Metrics][KV Offload] Fill vllm:kv_offload_config_info with the CPU cache capacity (#53902)
Signed-off-by: Amir Friedman <Amir.Friedman1@ibm.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-10-26 14:50:06 +02:00 |
|
|
|
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 |
|
|
Kfir ToledoandOr Ozeri
|
fe5fe8ba5f
|
[KV Offload] Load small CPU-tier hits synchronously within the step (#61961)
Signed-off-by: Kfir Toledo <kfir.toledo@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-10-26 11:16:30 +02:00 |
|
|
Sascha WirgesandClaude Opus 5.5
|
256d8b40d0
|
[Doc] Kolibri 1 reasoning and tool-call parsing via HF response template (#62885)
Signed-off-by: Sascha Wirges <sascha.wirges@aleph-alpha-research.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-26 08:27:15 +00:00 |
|
|
Jee Jee Li
|
4b1c04e76f
|
[Doc] Update Muse Spark Open (#63651)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-10-26 15:19:41 +08:00 |
|
|
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 |
|
|
Robert ShawandClaude Opus 5.5
|
41d9d1e14d
|
[Frontend] Add --reasoning-effort-map to rewrite request reasoning efforts (#61094)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-26 11:38:29 +08:00 |
|
|
Woosuk KwonandCodex
|
39e6a1aafc
|
[Benchmark] Include speculative drafting in bench forward (#63622)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-25 20:19:50 -07:00 |
|
|
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 |
|
|
Woosuk KwonandOpenAI Codex
|
237d2ffd08
|
[Benchmark] Add PCP support to vllm bench forward (#63613)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-10-25 14:25:55 -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 |
|
|
Chongmin Liandvllm-agent
|
b3466364b6
|
[Bugfix] Release cached cuBLAS workspaces after daemon warmup (#63451)
Signed-off-by: lichongmin <chongminli.cn@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-25 15:12:42 +00:00 |
|
|
|
94a29d316e
|
[Fast Start] Add daemon-to-daemon warmup cache seeding for Preload (#63088)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Xun Sun <UNIDY2002@outlook.com>
Co-authored-by: liusy58 <mg21330037@smail.nju.edu.cn>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-10-25 21:03:40 +08:00 |
|
|
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 |
|
|
|
65bc698356
|
[Bugfix][KV Offload] Reject misaligned chunked-local CPU suffix hits (#63266)
Signed-off-by: CharlesWu <296364977+charxwu@users.noreply.github.com>
Co-authored-by: CharlesWu <296364977+charxwu@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-25 12:18:49 +08:00 |
|
|
|
4e59165715
|
[Deprecation] Deprecate LM Format Enforcer structured outputs backend (#63423)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-24 15:19:14 -07:00 |
|
|
|
dd5e754494
|
[Profiling] Add support for profile_prefix payload in HTTP /start_profile endpoint (#51974)
Signed-off-by: Rushabh Lalwani <rlalwani@google.com>
Co-authored-by: Rushabh Lalwani <rlalwani@google.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-24 13:22:11 -07:00 |
|
|
|
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 |
|
|
|
c0ba7e01ff
|
[Perf][ROCm][Kernel] Add W4A8 int8-dot MXFP4 GEMV for RDNA3/RDNA3.5 d… (#60413)
Signed-off-by: Xiao Yu <xiao.yu.dc@outlook.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-24 12:09:43 +00:00 |
|
|
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 |
|
|
Woosuk KwonandClaude Opus 5.5
|
a50259bb32
|
[vLLM IR] Deprecate ir_op_priority ahead of vLLM IR removal (#63371)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-23 13:29:45 -07:00 |
|
|
Shyamal ShahandFlora Feng
|
a0544b13f2
|
[Docs][Mistral] Note that required and named tool choice may not produce a call (#63178)
Signed-off-by: Shyamal Shah <shyamals@nvidia.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-10-23 19:46:49 +00:00 |
|
|
albertoveneri
|
08aa305fb5
|
[Model] Add Domyn Edge support (#62544)
Signed-off-by: albertoveneri <214657570+albertoveneri@users.noreply.github.com>
Signed-off-by: Alberto <214657570+albertoveneri@users.noreply.github.com>
|
2026-10-23 17:31:57 +00:00 |
|
|
|
37cf712552
|
[Spec Decode] Keep drafters within their rotary cache on the V2 model runner (#63251)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Tianyao Wu <rayroy31@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-23 17:06:48 +00:00 |
|
|
YukioZzzandShanshan Shen
|
098eb89ea4
|
[ROCm][Kimi-K3] Support MoRIIO consumers with specialized decode (#63031)
Signed-off-by: Yichao Zhu <Yichao.Zhu@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-23 18:35:14 +08:00 |
|
|
|
8fae0ff58b
|
[Frontend] Accept images on /v1/systemone for multimodal next-token models (#62181)
Signed-off-by: Vigilans <vigilans@foxmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-10-23 07:30:02 +00:00 |
|
|
|
01ab87600e
|
[KV Connector][Mooncake] Expose transfer stats via Prometheus (#56939)
Signed-off-by: CAICAIIs <3360776475@qq.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-22 16:52:47 -07:00 |
|
|
Thirumaran
|
d0eb5d2f21
|
[Frontend] Expose --sleep-mode-backend on the CLI (#63138)
Signed-off-by: mramaran <mrmaran@protonmail.com>
|
2026-10-22 23:27:19 +00:00 |
|
|
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 |
|
|
|
c722f3a536
|
[Docs][KV Offload] Document canonical_layout in the KV offloading usage guide (#61822)
Signed-off-by: Liran Schour <lirans@il.ibm.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-22 14:37:41 -04:00 |
|
|
Andrew SansomandCodex
|
60a7d568f4
|
[Feature] [Frontend] [Reasoning] Support Prompt Embeds inputs for reasoning traces (#62765)
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Codex <codex@openai.com>
|
2026-10-23 02:04:18 +08:00 |
|
|
Krzysztof Tomalaandvllm-agent
|
f42421354d
|
[Model] Add Alpamayo 2 Super (reasoning model) (#62957)
Signed-off-by: Krzysztof Tomala <ktomala@nvidia.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-22 13:47:50 +00:00 |
|
|
|
fa72b61b55
|
[Security] Refresh Python and runtime CA certificates (#62868)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-10-22 02:47:39 -07:00 |
|
|
Ronald
|
12c01a22eb
|
[MoE] Revert platform hook for routed-expert capture rows (#62624) (#63013)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
|
2026-10-22 16:26:33 +08:00 |
|
|
Martin HickeyandPaul El Khoury
|
8420dd20fb
|
[Bugfix][Frontend] Cut stop strings and stop tokens on derender (#62719)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Paul El Khoury <82139421+pOpO1-9@users.noreply.github.com>
|
2026-10-22 13:27:46 +08:00 |
|
|
Hoai VoandClaude Opus 5.5
|
7e005d0f9c
|
[Model][LoRA] Enable LoRA support for BERT cross-encoders (#61279)
Signed-off-by: hoaivoke <vokehoai@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-22 04:33:09 +00:00 |
|
|
|
79d5c93796
|
[Feature][Pooling] Serve late chunking through /v1/embeddings (#61772)
Signed-off-by: Linze-Shi <linzeshi0@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-10-22 04:00:51 +00:00 |
|
|
|
ae43d045c4
|
[Bench] Save server queue time and TTFT in detailed results (#55809)
Signed-off-by: zhicheng Liu <lzc021026@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Roy Wang <jasonailu87@gmail.com>
|
2026-10-22 09:49:50 +08:00 |
|