Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• 83609ca91d [Doc]: fix typos in Python comments (#24173) 3 people 2025-09-04 17:52:17 +02:00
• e41a0fa377 [Perf] Freeze core engine proc heap after init (#24008) Nick Hill 2025-09-04 07:55:23 -07:00
• 37241077d5 [Misc] Removed force_fp8_e4m3fnuz from FP8LinearOp (#23725) nvjullinandLuka Govedič 2025-09-04 21:25:40 +08:00
• c9f7081f9c [LoRA]: Add lora support to qwen-2.5-omni (#24231) Yash Pratap Singh 2025-09-04 18:20:50 +05:30
• 16ded21eeb [XPU] support Triton Attention backend on Intel GPU (#24149) Kunshang Ji 2025-09-04 20:41:08 +08:00
• 2b30afa442 Use hidden_size_per_head as head_size fallback (#24221) nopperl 2025-09-04 20:59:16 +09:00
• eafa8dcde6 [Model] Add pp support for hunyuan (#24212) Jiangyun Zhu 2025-09-04 18:58:26 +08:00
• 6c7af8110a [Doc] Update vLLM Singapore Meetup info (#24234) TJian 2025-09-04 02:58:18 -07:00
• 8f423e5f43 [Feature][Response API] Add streaming support for non-harmony (#23741) Kebe 2025-09-04 18:49:06 +09:00
• 369a079568 [Hardware][Apple-CPU] Disable OneDNN build for Apple Silicon (#24200) Ignacio SicaandLi, Jiang <jiang1.li@intel.com> 2025-09-04 06:48:25 -03:00
• 402759d472 [Attention] FlashAttn MLA (#14258) 3 people 2025-09-04 05:47:59 -04:00
• 2c301ee2eb [Bugfix] Fix Incremental Detokenization with tokenizers == 0.22.0 (#24159) Fanli Linandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-04 17:47:08 +08:00
• 3efb9f4d95 [Attention][Platform] Refactor MLA to support Custom Op (#23332) whx 2025-09-04 17:46:37 +08:00
• 04f3c35cff Improve flexibility of auto_tune.sh execution. (#23766) anthonsuandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-04 02:41:41 -07:00
• 51d5e9be7d [Core][Model] Terratorch backend integration (#23513) 3 people 2025-09-04 08:22:41 +01:00
• e7fc70016f [Model] Add MiDashengLM model support (#23652) 3 people 2025-09-04 15:08:09 +08:00
• 12e1e63cc5 [Misc] Enhance output readability of helper script (#24214) Weida Hong 2025-09-04 14:38:26 +08:00
• 57b1ce94f7 [CPU] Refactor CPU unquantized linear (#24150) Li, Jiang 2025-09-04 14:28:45 +08:00
• cb55ad86fe Migrate ultravox inputs to TensorSchema (#23503) Benji Beck 2025-09-03 23:09:11 -07:00
• 712b273f65 [Refactor] Introduce basic Renderer for completion-style request (#24010) Flora Feng 2025-09-03 22:21:12 -07:00
• e919d6f549 [Kernel][Bugfix] Fix grouped topk cu (#24146) Qiming Zhang 2025-09-03 21:37:37 -07:00
• a38f8bd54c [Feature][Responses API]Support MCP tools with streaming mode + background mode (#23927) wuhang 2025-09-04 12:05:10 +08:00
• b5ee1e3261 Remove deprecated PyNcclConnector (#24151) Peter Pan 2025-09-04 06:49:16 +08:00
• 36c260dad6 [Feature][gpt-oss] Add support for num_cached_tokens and num_reasoning_tokens tracking (#23460) George Nagy II 2025-09-03 15:08:47 -06:00
• a43a3f1770 [Bugfix][DP] DP distribution does not require ray[default] (#23822) Kebe 2025-09-04 05:21:36 +09:00
• 6adaed42f4 [Feature][P/D]: Optimize NIXL Connector xfer Launch (#23887) WeiQing Chenandycyaw66 2025-09-04 03:14:30 +08:00
• a742322092 [Attention] Blackwell FP8 MLA support with CUTLASS_MLA backend (#23289) Matthew Bonanni 2025-09-03 14:05:24 -04:00
• 731a6940e3 Migrate whisper inputs to TensorSchema (#23505) Benji Beck 2025-09-03 11:04:00 -07:00
• e9b92dcd89 [Kernels] Overlap shared experts with send/recv (#23273) bnellnm 2025-09-03 12:35:18 -04:00
• fa4311d85f [V1] v1 engine + full CUDA graph support for PLaMo2 (#23998) 3 people 2025-09-04 00:24:02 +09:00
• 6d80ae83e1 [Bugfix] Fixing division by zero in triton_attn if query_heads/kv_heads > 16 (#23424) Burkhard Ringlein 2025-09-03 17:01:09 +02:00
• 4ba0c587ba FIX: Add libnuma-dev to Dockerfile for dev stage (#20388) dongbo910220 2025-09-03 22:17:20 +08:00
• 6997a25ac6 [Model] Remove useless code from MiniMax implementation (#23982) qscqesze 2025-09-03 19:27:04 +08:00
• 28f350e147 Support add_generation_prompt in embeddings endpoint with chat request (#23931) Jakub Smid 2025-09-03 12:47:55 +02:00
• 51383bd472 [CI] Accelerate mteb test by setting SentenceTransformers mteb score to a constant (#24088) wang.yuqi 2025-09-03 17:23:56 +08:00
• 9c99e4871f [Misc] Clean up deadcode for legacy processing pipeline (#24153) Isotr0py 2025-09-03 16:34:29 +08:00
• 70549c1245 [CI/Build] Serve images used by multimodal tests through local HTTP Server (#23907) dsinghviandCyrus Leung 2025-09-03 13:43:11 +05:30
• f0c503f66e [Nixl] Heterogeneous TP support FlashInfer (#20189) Nicolò Lucchesi 2025-09-03 09:19:54 +02:00
• f38035c123 [distributed][rl] remove nccl cumem env var override (#24141) youkaichaoandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-03 14:45:25 +08:00
• 426cc8629f [BugFix] Fix routed_scaling_factor double mul for dots1 and glm4 MoE models (#24132) Yong Hoon Shin 2025-09-02 21:57:59 -07:00
• e81d4e69c1 [Misc] Add check for dual_chunk_attention (#24070) Jiangyun Zhu 2025-09-03 12:19:14 +08:00
• 02d411fdb2 [Doc]: fix typos in Python comments (#24115) Didier Durand 2025-09-03 06:14:07 +02:00
• d7e1e59972 [Doc]: fix typos in Python comments (#24093) Didier Durand 2025-09-03 06:05:45 +02:00
• c4ed78b14f [Compile] Fix Compile Warning for w4a8_mm_entry.cu (#23660) Wentao YeandLuka Govedič 2025-09-02 23:45:52 -04:00
• 1bd007f234 fix some typos (#24071) co63oc 2025-09-03 11:44:50 +08:00
• 136d853e65 [V1] Wrapper which plumbs request-level logits processors into vLLM batch-level logits processing (#23656) afeldman-nm 2025-09-02 22:52:51 -04:00
• e32a0e8678 Upgrade xgrammar to 0.1.23 (#22988) Russell Bryant 2025-09-02 22:32:59 -04:00
• 42dc59dbac Update release pipeline post PyTorch 2.8.0 update (#24073) youkaichaoandHuy Do 2025-09-03 10:09:19 +08:00
• 862f2ef893 [XPU] Fix the bug of LoRA logits on the XPU platform (#24081) Chaojun Zhang 2025-09-03 08:21:18 +08:00
• 2fd1a40a54 [CI/Build] Disable SiluMul NVFP4 quant fusion tests (#24121) Matthew Bonanni 2025-09-02 19:50:28 -04:00
• 930a24144c [Bug] R1 Accuracy: Fix routed_scaling_factor Double Mul Issue (#24119) Wentao Ye 2025-09-02 18:22:30 -04:00
• 457e471971 [AMD][Kernel][Bugfix] Cast offsets tensor bn to tl.int64 to avoid GPU segfault (#23692) rasmith 2025-09-02 17:13:57 -05:00
• d328f7894f [CI] Enable all hf transformers baselines in test_hybrid (#23936) Thomas Parnell 2025-09-02 22:15:06 +02:00
• 98aee612aa [Log] Only Print Profiler Results on Rank 0 (#23370) Wentao Ye 2025-09-02 14:53:34 -04:00
• 598bd74cf8 Fix weights loading for Apertus (#24100) nathan 2025-09-02 20:34:28 +02:00
• 2417798471 [Metrics] Deprecate TPOT in favor of ITL (#24110) Mark McLoughlin 2025-09-02 19:10:10 +01:00
• 9480ae24e3 [Bugfix] Fix packed_factor missing attribute error (#23902) Kyuyeun Kim 2025-09-02 10:56:31 -07:00
• f399182e8c Run ruff format on a few files. (#24075) Chenheli Hua 2025-09-02 10:55:32 -07:00
• 1c41310584 [Bugfix] Fix transform_config parsing in Compressed Tensors (#23945) Kyle Sayers 2025-09-02 13:54:10 -04:00
• c83c4ff815 [Benchmark] Add support for local hf dataset path in benchmark (#23999) Jiangyun Zhu 2025-09-03 01:49:16 +08:00
• 0e1759cd54 [docs] add SYS_NICE cap & security-opt for docker/k8s (#24017) 3 people 2025-09-03 01:27:20 +08:00
• e66ed3e675 [CI Failure] Skip failing nvfp4 silu test (#23959) Michael GoinandWentao Ye 2025-09-02 13:18:15 -04:00
• e0653f6c0b [Model] Classification models support logit_bias / sigmoid_normalize (#24031) wang.yuqiandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-03 00:48:57 +08:00
• 38ba061f6f [BugFix] Fix EXAONE4 rotary embeddings (#23918) Kyungmin LeeandHarry Mellor 2025-09-02 23:40:55 +09:00
• 0a74e9d0f2 [Gemma3n] Fix audio batching (#24052) Nicolò Lucchesi 2025-09-02 16:23:35 +02:00
• 8bd5844989 correct LWS deployment yaml (#23104) Christian Berge 2025-09-02 14:04:59 +02:00
• ce30dca5c4 [CI]: reduce HTTP calls inside entrypoints openai tests (#23646) AzizandHarry Mellor 2025-09-02 12:49:32 +02:00
• 2f0bab3f26 [Model] Support dp on ViT on GLM-4.5V (#23168) WeiQing Chen 2025-09-02 18:48:18 +08:00
• fad73be1a5 [Doc]: fix typos in Python comments (#24077) Didier Durand 2025-09-02 11:38:55 +02:00
• 56d04089ef Migrate Interns1 inputs to TensorSchema (#23510) Benji Beck 2025-09-01 21:35:45 -07:00
• 7be0cb8e9e [XPU][Feature] fp8 online quantization support for XPU (#23148) Yan MaandQiming Zhang 2025-09-02 12:06:53 +08:00
• 1fa1d6a9a0 Migrate OvisImagePatchInputs to TensorSchema (#22024) Benji Beck 2025-09-01 21:01:36 -07:00
• d59c986444 Remove runtime checks based on pooling params (#24051) Maximilien de Bayser 2025-09-02 00:54:37 -03:00
• 04d0c60770 [Bugfix] Fix the issue that Blip2ForConditionalGeneration' object has… (#24028) damon 2025-09-02 11:54:20 +08:00
• 2b41cbbf03 [V1][Mamba1] - FP32 SSM Kernel Support (#23506) Asaf Joseph Gardin 2025-09-02 06:53:00 +03:00
• 0235103cbb [Doc]: fix typos in Python comments (#24042) Didier DurandandJee Jee Li 2025-09-02 04:07:45 +02:00
• a344a5aa0a [bugfix]fix MTP hidden states (#24056) Lucia Fang 2025-09-01 14:09:37 -07:00
• 5685370271 [Chore][V0 Deprecation] Move LogProb to a separate file (#24055) Woosuk Kwon 2025-09-01 12:07:53 -07:00
• a0e0efd6bd [Model] Support DP for ViT on Kimi-VL-A3B-Thinking-2506 (#23817) 4 people 2025-09-02 00:56:56 +08:00
• cf91a89dd2 [docs][misc] IOProcessor plugins fixes (#24046) Christian Pinto 2025-09-01 17:17:41 +01:00
• 39a22dcaac [Misc] Minor code simplification for spec decode (#24053) Woosuk Kwon 2025-09-01 08:54:01 -07:00
• 41c80698b3 Document multi-proc method selection for profiling (#23802) Julien Debache 2025-09-01 15:28:26 +02:00
• 7c8271cd1e [Model]: support KeyeVL-1_5-8B (#23838) Kwai-Keyeandwangruitao 2025-09-01 18:50:27 +08:00
• 3e330fcb21 [Doc]: Fix CPU install docs: force torch-backend=cpu to avoid GPU torchvision errors (#24033) Kay Yan 2025-09-01 18:34:52 +08:00
• d46934b229 [Frontend] Gemma3n audio transcriptions/translations endpoint (#23735) Nicolò LucchesiandCyrus Leung 2025-09-01 12:07:46 +02:00
• 107284959a [Doc]: fix typos in Python comments (#24026) Didier Durand 2025-09-01 11:38:20 +02:00
• dc1a53186d [Kernel] Update DeepGEMM to latest commit (#23915) Jee Jee LiandWentao Ye 2025-09-01 17:38:04 +08:00
• 55602bb2e6 [Frontend] Update the warning log when using VLLM_ALLOW_LONG_MAX_MODEL_LEN (#20904) wang.yuqiandHarry Mellor 2025-09-01 16:50:25 +08:00
• d7fbc6ddac [Misc] Enable V1 FP16 inference on pre-Ampere GPUs (#24022) Isotr0py 2025-09-01 16:12:22 +08:00
• 5438967fbc [Misc] add hash_function doc string (#24014) Ning Xie 2025-09-01 14:11:20 +08:00
• 422e793fa6 [Bugfix] Add support for <tool_call> format in streaming mode for XLAM Tool Parser (#22769) Code Jesus 2025-08-31 23:07:54 -07:00
• 1cb39dbcdd [Misc] IO Processor plugins for pooling models (#22820) Christian PintoandMax de Bayser 2025-09-01 07:07:12 +01:00
• 437c3ce026 Migrate Phi4 inputs to TensorSchema (#23471) Benji Beck 2025-08-31 23:05:59 -07:00
• 499b074bfd [Misc] refactor code by import as for torch._inductor.config (#23677) Ning Xie 2025-09-01 14:05:42 +08:00
• ff0e59d83a [CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357) Isotr0py 2025-09-01 13:52:20 +08:00
• b55713683c [Misc] Move fast prefill logic to separate method (#24013) Woosuk Kwon 2025-08-31 22:40:38 -07:00
• acc1a6e10a Fix the bug related to loading GPTP INT3 weights. (#23328) 3 people 2025-09-01 13:39:57 +08:00
• 8c742a66d1 [Misc] Avoid redundant copy for encoder-only models (#24012) Woosuk Kwon 2025-08-31 21:02:43 -07:00
• 183a70967a [BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994) JartXandIsotr0py 2025-09-01 05:33:40 +02:00
• 14b4326b94 v1: Support KV events from connectors (#19737) Or Ozeri 2025-09-01 04:13:21 +03:00