Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• 1e828573b4 [CI][Metrics] Stabilize tests with polling and subprocess guards (#34566) Andreas Karatzas 2026-02-16 04:52:02 -06:00
• a5ccc85c8c [Bugfix] Fix Dynamo unexpected keyword argument (#34320) Samu TamminenandWentao Ye 2026-02-16 11:32:30 +02:00
• b5475d0534 Revert "[Misc] fix qwen3.5 config" (#34610) Roger Wang 2026-02-16 01:06:05 -08:00
• 9521002f0a [Misc] fix qwen3.5 config (#34604) JJJYmmm 2026-02-16 16:25:38 +08:00
• ec17bdd894 [Renderer] Move InputPreprocessor into Renderer (1.5/2) (#34598) Cyrus Leung 2026-02-16 15:46:33 +08:00
• bb59c90248 [CI] Write bake config to temp directory instead of repo root (#34569) Amr Mahdi 2026-02-15 22:15:47 -08:00
• 5bff999d12 [Bugfix] Add method to swap quant_method on FusedMoE to fix LoRA issues (#34453) bnellnm 2026-02-15 23:10:50 -05:00
• bb85929aa6 [BugFix] Fix Python 3.13 FlashMLA import error (#34548) Lucas WilkinsonandJee Jee Li 2026-02-15 20:09:18 -08:00
• 5653021094 [Doc] Add Mistral-7b-v0.3 model to the batch invariance validated model (#34584) Parth Bansal 2026-02-16 05:09:00 +01:00
• 974d829b05 [CI][Frontend] Return 422 instead of 500 for invalid Anthropic tool_choice (#34590) Andreas Karatzas 2026-02-15 22:06:48 -06:00
• 91ac5d9bfd [CI/Build] Enable tests for recent day-0 new models (#34585) Isotr0py 2026-02-16 10:17:04 +08:00
• 23d825aba1 [torch.compile] Disable ar-rms fusion for ds3-fp4 & DP, fix CI test (#34392) Luka Govedičandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2026-02-15 09:33:57 -05:00
• f07a128413 [CPU][ARM] Add ARM BF16 cross-compilation support and improve documen… (#33079) Maryam TahhanandLi, Jiang <jiang1.li@intel.com> 2026-02-15 14:33:08 +00:00
• 71cd89264f [MM Encoder] Add Triton ViT attention backend (#32183) Isotr0py 2026-02-15 22:32:47 +08:00
• 19fab44152 [Doc] Update Encoder-Decoder models support doc with Florence-2 (#34581) Isotr0py 2026-02-15 20:18:57 +08:00
• 79c7e09235 [KV Connector] Add temporary, off-by-default VLLM_DISABLE_REQUEST_ID_RANDOMIZATION workaround (#34415) Seiji Eicher 2026-02-14 23:26:10 -08:00
• 79f3fab05a [Bugfix] Handle num_expert_group=None in flashinfer block-scale FP8 MoE (#34494) haosdent 2026-02-15 15:25:46 +08:00
• 604b9eaec5 [BUGFIX] Fix accuracy regression for NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 with TP>1 (#34476) Vadim Gimpelson 2026-02-15 11:25:17 +04:00
• 50dbd6c9e6 [bugfix] Fix critical bug when reporting for all paths where handler.create_error_response is used (#34516) 3 people 2026-02-15 12:24:25 +05:00
• 98bcc6ca59 [CI][Entrypoints] Validate detokenize token IDs to prevent int64 overflow causing 500 (#34468) Andreas Karatzas 2026-02-15 01:08:38 -06:00
• f13e86d8dd [Kernels] Fix Helion GPU utils to use platform-agnostic device name API (#34537) Andreas Karatzas 2026-02-14 22:29:23 -06:00
• 9ca768c740 [Model Runner V2] Minor cleanup for Sampler (#34563) Woosuk Kwon 2026-02-14 18:29:03 -08:00
• d5fe3f702c [Hybrid] Enable mamba prefix cache "align" mode with async scheduling (#33997) Thomas Parnell 2026-02-14 22:15:56 +01:00
• 73391a1baa [Renderer] Move InputPreprocessor into Renderer (1/2) (#34510) Cyrus Leung 2026-02-15 02:14:21 +08:00
• b3c14229b0 [ROCm][CI] Guard sparse MLA backend imports for ROCm compatibility in tests (#34538) Andreas Karatzas 2026-02-14 09:32:09 -06:00
• 2f186635cb [Bugfix] Fix Qwen3.5 config loading (#34554) Roger Wang 2026-02-14 03:56:11 -08:00
• 342a7cda2d [Misc] Update tests and examples for Prithvi/Terratorch models (#34416) Christian PintoandCyrus Leung 2026-02-14 07:03:51 +00:00
• d1ea65d0a1 [new model] add COLQwen3 code & Inference (#34398) Kata Coder 2026-02-14 13:15:19 +09:00
• de42abb366 [CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294) Andreas Karatzas 2026-02-13 22:04:29 -06:00
• 60ca7981bc Add explicit validation error for tool calls. (#34438) Julien Denize 2026-02-14 05:04:01 +01:00
• 0ef5b9147b fix: use __annotations__ instead of get_type_hints() for dynamic kwargs detection (#34527) Christian S. PeroneandCyrus Leung 2026-02-14 04:03:37 +00:00
• ed242652d7 [bug] Make sure get_modality_with_max_tokens is deterministic (#34533) Shiyan Deng 2026-02-13 20:02:59 -08:00
• b37b679770 [Feature][Perf] Support Selective CPU Weight Offloading (#34535) Wei Zhao 2026-02-13 23:02:24 -05:00
• a0638d052d [Bugfix] Fix ROCm UVA CPU weight offloading broken by #32993 (#34543) Andreas Karatzas 2026-02-13 22:01:42 -06:00
• c027541eaf [Hybrid] Enable spec decoding in mamba cache align mode (#33705) Harry Huang 2026-02-14 05:02:28 +08:00
• fd267bc7b7 [Bugfix]: Fix structured output in multi-turn gpt-oss (#34454) 3 people 2026-02-13 14:12:48 -05:00
• bfaa559305 Revert "[Bugfix] Fix fused MoE IMA (sans chunking) by using int64 for strides" (#34530) Michael Goin 2026-02-13 13:35:29 -05:00
• 87789c8364 [Misc] vLLM's --enforce-eager should turn off compile and cudagraphs only (#34523) Richard Zou 2026-02-13 12:52:20 -05:00
• bcd65c1f6a [Bugfix] Replace c10::optional with std::optional in topk kernel (#34467) Pushpinder Singh 2026-02-13 08:30:23 -08:00
• 59d53066d8 [Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993) Wei ZhaoandMichael Goin 2026-02-13 11:11:26 -05:00
• 4a9952ec1b [Bugfix] Add quant_config in ViT of Kimi-K2.5 (#34501) LoganJaneandIsotr0py 2026-02-14 00:05:34 +08:00
• 1dae7b7843 [Bugfix] Exclude language_model_only key from MM AOT compile hash but include in model one (#34508) Roger Wang 2026-02-13 05:59:00 -08:00
• 5885e330ef [Misc] Port Qwen3.5 Configs (#34512) Roger Wang 2026-02-13 05:24:25 -08:00
• 071d863e20 Extend ColBERT support to non-standard BERT backbones (#34170) Ilya Boytsov 2026-02-13 10:53:09 +01:00
• 0916e7960b [GDN] Use CPU tensors to build GDN metadata (#34498) Woosuk Kwon 2026-02-13 01:24:45 -08:00
• 3d2a026fd0 [Feature] Pipeline Parallel Async send/recv, 2.9% E2E throughput improvement (#33368) Wentao YeandNick Hill 2026-02-13 03:38:16 -05:00
• dddbff4624 [Core] Move pause and resume functions into engine (#34125) 3 people 2026-02-13 00:15:10 -08:00
• 47e9b63e1a [KVConnector] Clean up redundant code in KV connectors (#34147) Martin Hickey 2026-02-13 08:14:30 +00:00
• 934acddef9 [Perf] fused_moe: add int4_w4a16 benchmark support and tuning config (#34130) Matthias GehreandTJian 2026-02-13 09:14:27 +01:00
• 742d214d6e [Bugfix] fix the import path in moe test utils.py (#34245) Marek Michalowski 2026-02-13 08:13:45 +00:00
• 4137c5dfa7 [Bug Fix] Fix MambaManager.cache_blocks() crash on null blocks in align mode (#34418) haosdent 2026-02-13 16:13:22 +08:00
• 7a8a46ddcb [BugFix] Fix and optimize max_num_blocks_per_req calculation for MambaSpec (#34440) Harry Huang 2026-02-13 16:13:14 +08:00
• bcf0731aa0 [New Model] support new model ovis2.6 (#34426) myselvess 2026-02-13 16:12:45 +08:00
• ec090c2429 [Refactor] Call renderer for online IO processor request (#34490) Cyrus Leungandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2026-02-13 14:48:45 +08:00
• eea3024f43 [Bugfix] Fix mamba state dtype setting for Qwen3-Next and Qwen3.5 (#34489) Roger Wang 2026-02-12 22:48:42 -08:00
• 2f308214c0 [Refactor] Pass full VllmConfig to Renderer (#34485) Cyrus Leung 2026-02-13 14:48:38 +08:00
• 1b4e8e53f8 [CI/Build] Fix CUDA re-initialization error in distributed model tests (#34491) Cyrus Leung 2026-02-13 14:43:53 +08:00
• dcf6ee8592 [Bugfix] Fix encoder cache underestimation for GLM-4V/GLM-OCR single image (#34483) haosdent 2026-02-13 13:04:06 +08:00
• 372b2e762a [Bugfix] Standardize getting number of image patches/tokens (#34358) Cyrus Leung 2026-02-13 12:47:01 +08:00
• 6afa587d31 [ROCm][CI] Fix serving tokens test failures (#34047) Andreas Karatzas 2026-02-12 21:27:53 -06:00
• 94ed6cf6ea Add new sections to CODEOWNERS (#34309) Cyrus Leung 2026-02-13 10:39:28 +08:00
• bf37812ca7 [Hybrid] Fix and optimize block-aligned splitting in mamba cache align mode (#33706) Harry Huang 2026-02-13 10:21:52 +08:00
• b86bf4417e [Bugfix] Fix Random Dataset Prefix Length Inaccuracy (#33907) Frank WangandRoger Wang 2026-02-12 18:21:19 -08:00
• de13dd781f [Kernel] [Helion] [5/N] Add Helion Autotuning infrastructure (#34025) Yanan Cao 2026-02-12 18:21:05 -08:00
• 62788f99a4 [Bugfix] Delete unused redundant code in Kimi-K2.5 (#34427) LoganJaneandIsotr0py 2026-02-13 10:18:42 +08:00
• ea5ff3a1f6 [Refactor] Simplify BOS/EOS token handling (#34435) Cyrus Leung 2026-02-13 10:18:24 +08:00
• 04ea31baab [Bugfix] Remove assert that's no longer valid (#34443) bnellnm 2026-02-12 21:18:15 -05:00
• 6f019e6e0a [BugFix] Add block_size validation for mamba cache align mode (#34445) Harry Huang 2026-02-13 10:18:07 +08:00
• d707678dfb Fix num_logprobs parameter description in sampler.py (#34451) Zhuohan Li 2026-02-12 18:18:03 -08:00
• fc22cae4ac [CI/Build] Update video URLs for testing (#34446) Cyrus Leung 2026-02-13 10:15:36 +08:00
• 96161fe978 [Kernel] [Helion] [4/N] Add silu_mul_fp8 Helion kernel (#33373) Yanan Cao 2026-02-12 18:13:12 -08:00
• 4453ba8d9e [Core] Profiler improvements and lazy initialization (#33198) JaewonandLu Fang 2026-02-12 16:16:38 -08:00
• aa181c923b [Core] Add sleep level 0 mode with enqueue/wait pattern (#33195) JaewonandLu Fang 2026-02-12 16:16:25 -08:00
• be7370daf3 [Frontend] Enable generic structured_outputs for responses API (#33709) Alec SandAlec Solder 2026-02-12 19:15:48 -05:00
• 9ea1f598ce Use paged_attention_v1 for sliding window decode in rocm_aiter_fa (#34378) Mengtao (Martin) YuanandMartin Yuan 2026-02-12 16:14:43 -08:00
• f120bd42d3 [Kernel] Support Flashinfer trtllm fused MoE non gated FP8 & NVFP4 (#33506) amitz-nv 2026-02-12 23:06:58 +02:00
• fac4e96940 small adjustment to wvSplitKrc (#34410) Hashem Hashemi 2026-02-12 12:26:36 -08:00
• 6d4e27ce29 [Bugfix] Enforce DeepGEMM when using sparse_attn_indexer on CUDA (#34374) Michael Goin 2026-02-12 15:08:06 -05:00
• 4c078fa546 [ROCm][CI] Pin TorchCodec to v0.10.0 for ROCm compatibility (#34447) Andreas Karatzas 2026-02-12 12:47:34 -06:00
• 6c0baee610 [Voxtral Realtime] Refactor & Improve buffering logic (#34428) Patrick von Platenandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2026-02-12 18:46:43 +01:00
• 1100a97621 [Voxstral Realtime] Enable tests (#33803) Patrick von Platen 2026-02-12 18:43:24 +01:00
• 766e167821 [ROCm][quantization] improve OCP weight quant parser robust (#34431) xuebwang-amdandTJian 2026-02-13 01:40:19 +08:00
• becbe24808 [Bugfix] Remove broken raw url GGUF model loading support (#34433) Isotr0py 2026-02-13 01:40:01 +08:00
• 679ca5d8d3 Fix MoE for the Transformers modelling backend (#34436) Harry Mellor 2026-02-12 18:29:42 +01:00
• f2c47886fd [Attention] Add FlashInfer Sparse MLA backend (#33451) 3 people 2026-02-12 12:21:54 -05:00
• 334c715e0f [Docs] Spec decoding docs warning removal (#34439) Nicolò Lucchesi 2026-02-12 18:01:51 +01:00
• 7b5a8b4a9d [BUG] Reset running requests when clearing cache for pause/resume (#34382) Aaron Hao 2026-02-12 08:19:13 -08:00
• dea63512bb Add config file for fused MoE for Nemotron (TP4, B200) (#34411) danisereb 2026-02-12 16:09:55 +02:00
• 8a798be929 [ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update aiter (#34192) 4 people 2026-02-12 07:06:33 -06:00
• fb455ed547 [V0 Deprecation] Remove code related to per-request logits processors (#34400) Cyrus Leung 2026-02-12 20:44:28 +08:00
• f5897613fb Fix Mistral config remap to accept compressed-tensors quantization #34028 (#34104) baonudesifeizhai 2026-02-12 03:22:06 -05:00
• 55a1a9563a Vllm CPU benchmark suite improvement (#34128) Louie Tsai 2026-02-12 00:04:44 -08:00
• 386bfe5d08 [bugfix] refactor FunASR's _get_data_parser (#34397) AllenDouandzixiao 2026-02-12 15:26:49 +08:00
• e9cd691132 [Bugfix] Fix Sparse24 Compressed Tensors models (#33446) Kyle SayersandMichael Goin 2026-02-12 02:15:16 -05:00
• 80f2ba6ea6 Fix DeepSeek-OCR tensor validation for all size variants (#34085) Yichuan WangandCursor 2026-02-11 22:50:23 -08:00
• 136b0bfa59 [BugFix] Fix DP chunking (#34379) Lucas WilkinsonandBill Nell 2026-02-11 23:44:03 -07:00
• b96f7314b4 [Refactor] Pass Renderer to Input Processor (#34329) Cyrus Leung 2026-02-12 11:38:11 +08:00
• ced2a92f40 [Refactor] Move validation to params definitions (#34362) Cyrus Leung 2026-02-12 11:33:15 +08:00
• e1d97c38f8 [Bug Fix] Fix naive_block_assignment always defaulting to False due to arg misalignment (#33848) Runkai Tao 2026-02-11 22:30:57 -05:00
• ec12d39d44 [Bugfix] Fix MTP accuracy for GLM-5 (#34385) Michael Goin 2026-02-11 22:08:19 -05:00