Commit Graph
10211 Commits
Author SHA1 Message Date
Yu Jiaqi 0552cfb195 [Model] Siglip Embedding Support (#27324)
Signed-off-by: piood <2477084691@qq.com>
2025-10-23 20:19:48 +00:00
KebeandRui Qiao 51dd14ac2b [Bugfix][DP] Fix creating too many DP Placement Groups (#26880)
Signed-off-by: Kebe <mail@kebe7jun.com>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>
2025-10-23 20:16:51 +00:00
Matthew Bonanni dbfbf9f324 [Attention] Fix FlashMLA metadata builder arguments for q_len > 1 (#27368)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-23 15:58:15 -04:00
Jonathan Chen ca76486a16 [Chore] Separate out vllm.utils.platform_utils.py (#27374)
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
2025-10-23 19:08:06 +00:00
Isotr0py 81d5bb765a [Bugfix] Fix AWQ marlin layer skipping (#27416)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-23 18:30:28 +00:00
Gregory Shtrasberg 0825197bee [Bugfix][ROCm][DeepSeek] Fix for forward_hip in rope for DeepSeek (#27373)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-10-23 17:43:53 +00:00
Alexander Matveev 9ef3d5b875 [Bugfix] Fix dp_chunking enablement logic in FusedMoE layer (#27220)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-10-24 00:03:14 +08:00
wang.yuqigemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Christian Pinto
3fa2c12185 [Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>
2025-10-23 14:46:18 +00:00
Cyrus Leung fe2016de2d [CI/Build] Remove unnecessary flags from test registry (#27353)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-23 14:42:40 +00:00
Ilya MarkovandTyler Michael Smith 237cf6d32a [Misc] Remove use of CUDA_VISIBLE_DEVICES for device selection (fix DP slow startup time &c) (#26709)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
2025-10-23 20:58:39 +08:00
Navya SrivastavaandHarry Mellor faee3ccdc2 [Feature] Pydantic validation for speculative.py (#27156)
Signed-off-by: Navya Srivastava <navya.srivastava1707@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-23 12:19:33 +00:00
570c3e1cd4 [Bugfix] Honor --mm_encoder_attn_backend when used (#27124)
Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-23 20:09:52 +08:00
tomeras91 61089465a6 [Model] Add MoE support for NemotronH (#25863)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
2025-10-23 10:27:23 +00:00
Tova Movshovitz 88afa11010 [Metrics] [KVConnector] Add connector prefix cache hit rate stats (#26245)
Signed-off-by: tovam <tovam@pliops.com>
2025-10-23 12:21:08 +02:00
Lucia Fang fc059c7061 [Bugfix] Fix args settings for guided decoding args (#27375)
Signed-off-by: Lucia Fang <fanglu@fb.com>
2025-10-23 07:34:06 +00:00
Jonathan Chen e255d92990 [Chore] Remove duplicate has_ functions in vllm.utils (#27372)
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
2025-10-23 06:11:59 +00:00
wang.yuqi 3729ed00ba [Model] Add num_cached_tokens for PoolingRequestOutput (#27378)
Signed-off-by: wang.yuqi <noooop@126.com>
2025-10-23 14:03:42 +08:00
Giancarlo DelfinandNick Hill 6644796bf4 [V1][spec decode] return logprobs for spec decoding (#26060)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-10-22 22:59:59 -07:00
Andrew Sansom ff93cc8c84 [CORE] Support Prefix Caching with Prompt Embeds (#27219)
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
2025-10-22 22:18:07 -07:00
PiteXChen 243ed7d32e [Bugfix][Core] running queue index leakage exception (#26754)
Signed-off-by: CLFutureX <chenyongqyl@163.com>
2025-10-22 21:40:12 -07:00
Cyrus Leung 6738e4a093 [Bugfix] Fix SLA tuner initialization (#27355)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-22 20:43:04 -07:00
Isotr0py 2566dca2a9 [Bugfix] Fix deepseek-ocr multi-image inference and add merge_by_field_config=True with tensor schema support (#27361)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-22 17:15:38 -07:00
dongbo910220andCyrus Leung a0003b56b0 [Chore] Separate out system utilities from vllm.utils (#27201)
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-10-22 20:25:25 +00:00
Daisy-Ma-coderandqqma 5beacce2ea [BugFix] bugfix for Flash Attention MLA with full cuda graph IMA following pr-25490 (#27128)
Signed-off-by: qqma <qqma@amazon.com>
Co-authored-by: qqma <qqma@amazon.com>
2025-10-22 19:36:39 +00:00
rongfu.lengandCyrus Leung 8669c69afa [Feature] publisher default set zmq in kv_event config (#26915)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-10-22 19:19:33 +00:00
Sage 1651003c35 [Prefix Cache] Use LoRA name for consistent KV-cache block hashing (#27211)
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2025-10-22 18:13:03 +00:00
Luciano MartinsandLuciano Martins e05a6754a8 [Model] Revert PR #26715: Restore custom PaliGemma and Gemma3-MM impl… (#27309)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
2025-10-22 10:05:34 -07:00
Isotr0py 084a9dae80 [Bugfix] Disable FlexAttention direct block mask building for encoder-only models (#27344)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-22 16:39:08 +00:00
c9461e05a4 Support Anthropic API /v1/messages Endpoint (#22627)
Signed-off-by: liuli <ll407707@alibaba-inc.com>
Co-authored-by: liuli <ll407707@alibaba-inc.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-10-22 09:13:18 -07:00
Nicolò Lucchesi 4dfdb821c8 [P/D] Dynamic kv_output_aggregator collect size (#26734)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-10-22 18:07:58 +02:00
Russell BryantandDarkLight1337 58fab50d82 [Frontend] Require flag for loading text and image embeds (#27204)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-22 15:52:02 +00:00
Isotr0py db6f28d898 [Bugfix] Fix HF format InternVL large variants video processing (#27330)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-22 08:39:23 -07:00
Cyrus Leung 14e2f1231e [Bugfix] Make get_mrope_input_positions instance methods (#27342)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-22 08:38:34 -07:00
Chendi.XueandNicolò Lucchesi 7c4767f1eb [NIXL] use Host buffer to support TP_ratio > 1 for XPU (#27140)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
2025-10-22 15:28:13 +00:00
Jee Jee Li 9771e0b432 [Bugfix] Add missing 'is_internal_router' attribute to FusedMoEWithLoRA (#27351)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-22 08:19:12 -07:00
Reinforce-IIandWentao Ye 980de31ca0 [bugfix] remove unused parameters to reduce unnecessary vram usage (#26789)
Signed-off-by: Reinforce-II <fate@eastal.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2025-10-22 08:16:09 -07:00
Wentao Ye 1c160841ea [Bug] Fix DeepSeek-V2.5-1210-FP8 issue (#27267)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-22 11:00:10 -04:00
Mark McLoughlin 4ca13a8667 [NIXL] Terminate handshake listener thread in shutdown (#26404)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-10-22 16:59:53 +02:00
Isotr0pyandRoger Wang 675aa2ec64 [Model] Upstream Deepseek-OCR model (#27247)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-22 07:59:15 -07:00
3ae082c373 [Chore] Separate out optional dependency checks from vllm.utils (#27207)
Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-10-22 10:44:21 -04:00
Jee Jee Li abf3db40ef [Core] Handle MoE LoRA edge cases (#27335)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-22 13:14:33 +00:00
gnovackandJee Jee Li 8e4ca4d14e Bugfix - pass 'max_num_tokens_padded' into 'moe_lora_align_block_size' (#27311)
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-22 12:23:57 +00:00
Wentao Ye 1a0f4defb7 [Log] Add Warning for LLM(data_parallel_size=k) single-process DP Usage (#27282)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-22 12:12:21 +00:00
Li, Jiang 843af7f7fc [Bugfix][CPU] Disable dual stream execution for experts on CPU (#27320)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-10-22 11:02:27 +00:00
wang.yuqigemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Cyrus Leung
1f633b8632 [Frontend][3/N] Improve all pooling task | Support binary embedding response (#27066)
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-10-22 18:38:57 +08:00
a4c29e6e82 fixed reasoning streaming with tool_choice="required" (#24108)
Signed-off-by: CNE Pierre FICHEPOIL <pierre-1.fichepoil@gendarmerie.interieur.gouv.fr>
Signed-off-by: ExtReMLapin <3909752+ExtReMLapin@users.noreply.github.com>
Co-authored-by: CNE Pierre FICHEPOIL <pierre-1.fichepoil@gendarmerie.interieur.gouv.fr>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2025-10-22 09:42:55 +00:00
wangxiyuan f6027b2855 [1/N][Platform] Cleanup useless function (#26982)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-10-22 09:04:57 +00:00
Jiangyun Zhu ab3e80042e [torch.compile] Enable silu_mul_fp8_quant fusion without custom ops enabled (#27146)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
2025-10-22 00:22:39 -04:00
Cyrus Leung ceacedc1f9 [Benchmark] Add plot utility for parameter sweep (#27168)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-21 20:30:03 -07:00
LainandDaniel Campora 09a7e6f617 [Deepseek v3.2] Remove extra logics in indexer (#26465)
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Lain <siyuanf@nvidia.com>
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
2025-10-21 23:34:03 +00:00