iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
14,386 Commits 3 Branches 0 Tags
fa6a6be51978bd4b49ba0da17039e60f96dc5b13
Commit Graph
10211 Commits
Author SHA1 Message Date
Tyler Michael Smith 6c2eef5a5d [P/D] KVConnector for decode benchmarking (#25986) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-10-21 16:30:47 -07:00
Benjamin Chislett 19748806f0 [Bugfix] skip cuda graph for drafter when running with eager (#26821) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-10-21 15:39:09 -07:00
ExtReMLapinCNE Pierre FICHEPOILgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 		4a8a567e16 Updated xgrammar backend to not deny supported string formats (#27253) 
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: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-21 22:25:23 +00:00
Alexander Matveev 344a0017c0 [Performance] Dual stream execution of "shared_experts" and "selected_experts" inside FusedMoE (#26440) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-10-21 21:38:29 +00:00
Tao HeandLucas Wilkinson 250fb1b8ea [Bugfix] fixes the decoding metadata of dense mla's fp8 kvcache. (#27144) 
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-10-21 18:27:03 +00:00
Nick Hill 647214f3d5 [V0 Deprecation] Remove V0 executors (#27142) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-10-21 11:09:37 -07:00
David Whyte-Gray ddeec11ba9 [Bugfix][P/D] Reduce num_threads used by nixl ucx backend (#27196) 
Signed-off-by: David Whyte-Gray <40244437+dagrayvid@users.noreply.github.com>
 2025-10-21 13:41:52 -04:00
Wentao Ye 86ed77022d [Feature] Batch Invariant for R1 TP 8 on Blackwell (#27229) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-21 10:25:55 -07:00
JartX ba09652de2 [ROCM] Enable CompressedTensorsWNA16 (#27187) 
Signed-off-by: JartX <sagformas@epdcenter.es>
 2025-10-21 10:43:23 -04:00
dongbo910220 6c728f7771 [Chore] Separate out NCCL utilities from vllm.utils (#27197) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
 2025-10-21 06:18:23 -07:00
Daniel Cámpora 80e9452984 [Deepseek v3.2] Optimize top_k_per_row (#26763) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
 2025-10-21 08:30:07 +00:00
Roger Wang c3a2c6ac5f [MM][Core] Decouple ViT backend from LM backend (#27061) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-10-21 00:30:10 -07:00
Nicolò Lucchesi 72f431e709 [Nixl] Minor refactor to handshake related metadata (#26410) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-10-21 09:07:47 +02:00
Zebing Lin be4445072c [Fix][Spec Decode] Fix llama4 draft loading with different quantization (#27136) 
Signed-off-by: linzebing <linzebing1995@gmail.com>
 2025-10-20 23:19:00 -07:00
Benjamin Chislett f381cf2302 [Bugfix] Fix broken MTP weight loading for FP8 KV Scales (#27227) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-10-20 22:51:44 -07:00
Varun Sundar RabindranathVarun Sundar RabindranathMichael Goin
 		5ff5d94e77 [Bugfix] Fix gpt-oss w4a8 DP/EP on B200 (#26729) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-10-21 01:51:14 -04:00
Shu WangandMichael Goin f95da13c3d [ModelOpt] Load w13/w2_input_scale for all experts, nvfp4 (#26135) 
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-10-21 01:50:31 -04:00
Po-Han Huang (NVIDIA) aef368aa08 [BugFix] GPT-OSS Attention DP + MoE TP weight loading issue (#24032) 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
 2025-10-21 04:03:47 +00:00
Chen WuwuchenNathan Van GheembanjuedeDanielle RobinsonJee Jee Libk-201
 		5f6cbf60d6 [Feature][Kernel]FusedMoE LoRA (#21229) 
Signed-off-by: wuchen <cntryroa@gmail.com>
Signed-off-by: banjuede <lmklhc@163.com>
Signed-off-by: Chen Wu <cntryroa@gmail.com>
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: bk-201 <joy25810@foxmail.com>
Co-authored-by: wuchen <wuchen@zetyun.com>
Co-authored-by: Nathan Van Gheem <vangheem@gmail.com>
Co-authored-by: banjuede <lmklhc@163.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: bk-201 <joy25810@foxmail.com>
 2025-10-21 03:01:37 +00:00
Russell BryantandIsotr0py 3ada34f9cb [Frontend] Enforce tokenize=False when applying chat template (#27205) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-10-21 02:57:34 +00:00
Lunwen HeandLunwen He 0eb8f2b880 create is_in_the_same_node on cpu (#26832) 
Co-authored-by: Lunwen He <lunwenh@meta.com>
 2025-10-21 02:04:14 +00:00
Fadi ArafehandMichael Yang 163965d183 [cpu] Dispatch un-quantized linear to oneDNN/ACL by default for AArch64 (#27183) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Michael Yang <Michael.Yang@arm.com>
 2025-10-21 02:02:58 +00:00
Nick Hill a03cf9bc70 [V0 Deprecation] Remove V0 metrics code (#27215) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-10-21 02:02:10 +00:00
Isotr0py 352c0c8a28 [Quantization] Automatically infer AWQ modules_to_not_convert field (#26909) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-10-21 01:49:28 +00:00
Heng Guoandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 87778d5f00 [Feature][Quantization] auto_round support for mixed bits quantization (#23812) 
Signed-off-by: n1ck-guo <heng.guo@intel.com>
Signed-off-by: Heng Guo <heng.guo@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-20 22:23:30 +00:00
shivampr 4d0f266113 [Kernel][Model] Tune fused_moe Triton configs for Qwen3-30B A3/A3B on H100 (FP8/BF16) (#26268) 
Signed-off-by: Shivam <shivampr.dev@gmail.com>
 2025-10-20 07:48:01 -07:00
Eugene KhvedchenyaNatan BagrovRoger Wang
 		e93ff6c8b9 Nemotron Nano V2 VL + EVS Video Support (#27107) 
Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
Signed-off-by: Natan Bagrov <nbagrov@nvidia.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Natan Bagrov <nbagrov@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-10-20 22:19:11 +08:00
Jiangyun Zhu 9fce7bee74 [Kernel] Accelerate solve_tril with TMA (#26746) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-10-20 05:39:02 +00:00
Andy LoandJee Jee Li b63f2143f8 [LoRA] LoRA cuda graph specialization (#25914) 
Signed-off-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-10-20 04:21:09 +00:00
Yi Zhanggemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Roger Wang
 		f32bf7582e [Model][VLM] Support Bee-8B Model (#27012) 
Signed-off-by: uyzhang <yi.zhang.4096@gmail.com>
Signed-off-by: Yi Zhang <zhangyi970819@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-10-20 02:31:26 +00:00
Yongtao Huang 8a81d776ce Fix typo in ValueError message: use kv_role instead of kv_disagg_role (#27166) 
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
 2025-10-19 19:47:19 +00:00
Sergei Skvortsov f6fdacd82c [Bugfix] Fix error with penalties when speculative decoding and structural output are enabled (#26586) 
Signed-off-by: southfreebird <yvorott@gmail.com>
 2025-10-19 19:24:46 +00:00
Cyrus Leung d31f7844f8 [Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-19 05:20:55 -07:00
iAmir97andiAmir97 7a6c8c3fa1 [Chore] Separate out vllm.utils.network_utils (#27164) 
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
 2025-10-19 03:06:32 -07:00
Jianyu Huang 221bf72577 output type conversion fix (#27159) 2025-10-19 08:10:07 +00:00
Cyrus Leung b3aba04e5a [Benchmark] Convenience script for multiple parameter combinations (#27085) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-18 23:57:01 -07:00
dongbo910220 8a297115e2 [Chore] Separate out hashing utilities from vllm.utils (#27151) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
 2025-10-19 11:09:38 +08:00
22quinn 191eed0bb9 [BugFix] Fix lazy imports involving outlines_core (#27158) 
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
 2025-10-19 02:35:32 +00:00
Woosuk Kwon fb860670da [Minor] Remove unused env variable (#27161) 2025-10-18 18:48:35 -07:00
Tova Movshovitz 83e760c57d [V1][Metrics][Plugin] Add plugin support for custom StatLoggerBase implementations (#22456) 
Signed-off-by: tovam <tovam@pliops.com>
 2025-10-18 15:12:46 -07:00
Lucas Wilkinsonandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> c2bba69065 [BugFix] Disable fp8 kv-cache by default for DeepSeek V3.2 (#27121) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-18 22:05:23 +00:00
Boyuan Feng e133d6d218 [BugFix] fix graph partition signature (#27139) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-10-18 17:34:36 -04:00
dongbo910220 a1946c9f61 [Chore] Separate out profiling utilities from vllm.utils (#27150) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
 2025-10-18 19:12:01 +00:00
Nick Hill 3b45075206 [Minor] Add some clarifying comments to recent changes (#27130) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-10-18 09:52:45 -07:00
Yongtao Huang 168e578efc Fix incorrect string formatting in barrier timeout exceptions (#27149) 
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
 2025-10-18 09:51:57 -07:00
Isotr0py 6ac5e06f7c [Chore] Clean up pytorch helper functions in vllm.utils (#26908) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
 2025-10-18 09:48:22 -07:00
Lukas Geiger 5c2acb270a [Models][QwenVL] Remove unnecessary .contiguous() calls (#27106) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-10-18 07:05:05 -07:00
Nicolò Lucchesi b26b70bec4 [Misc] Refactor get_kv_cache_spec into AttentionLayerBase (#26587) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-10-18 13:51:21 +00:00
Fadi Arafeh ab4be40fc5 [fix][cpu] fix prefill attention in CPU attention backend (#27035) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2025-10-18 13:30:21 +00:00
Wentao Ye 245e4f2c01 [Feature] Batch Invariant: Support DeepGEMM and Blackwell (#27127) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-18 09:28:05 -04:00