Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• 1116590b16 [gpt-oss] Validate gpt-oss python tool during initialization (#23856) Chen Zhang 2025-09-09 01:37:48 -07:00
• ccb97338af [Misc] Add Codex settings to gitignore (#24493) Roger WangandRoger Wang 2025-09-09 01:25:44 -07:00
• 45c9cb5835 [Misc] Add claude settings to gitignore (#24492) Ye (Charlotte) Qi 2025-09-09 01:14:45 -07:00
• e283976f3a [Performance][MM] Building the inverse permutation in O(n) time in Qwen2_5_VisionTransformer (#24443) WeiQing ChenandJunhong 2025-09-09 15:24:11 +08:00
• 46876dff32 [Doc]: fixing typos to improve docs (#24480) Didier Durand 2025-09-09 08:06:04 +02:00
• 1823a00d67 [Misc] Support bench serve long context (#24373) Ming Yang 2025-09-08 22:53:10 -07:00
• ed16d0f26f [Doc] mention fpdb for multiprocess breakpoints (#24452) Mickaël Seznec 2025-09-09 06:46:45 +02:00
• 0cdd213641 [Misc] Improve Worker process title and logging prefix (#22205) 22quinn 2025-09-08 21:43:48 -07:00
• 948dd3443b [Bugfix] Fix Apertus HF repo name (#24447) Cyrus Leung 2025-09-09 12:40:29 +08:00
• b2f7745774 Add data_parallel_size to VllmConfig string representation (#24298) cong-metaandCong Chen 2025-09-08 21:35:18 -07:00
• 82dfb12e52 [Core] Use sha256 bytes instead of BlockHash to reduce GC overhead (#23673) Zebing Lin 2025-09-09 00:34:37 -04:00
• bba1042c6f [Flashinfer] Support Flashinfer TRTLLM FP8-qkv BF16/FP16-out Attention Kernel (#23647) elvischenv 2025-09-09 11:53:07 +08:00
• b6fbc15634 [BugFix][Model] Fix Ernie4.5-VL hanging on long inputs (#24074) CSWYF3634076 2025-09-09 11:37:16 +08:00
• 3e0d4a3475 Move KVTransferConfig from config/__init__.py to config/kv_transfer.py (#24434) Harry Mellor 2025-09-09 04:30:32 +01:00
• 562663a044 Bump actions/github-script from 7.0.1 to 8.0.0 (#24413) 3 people 2025-09-09 03:12:44 +00:00
• ed1623a88a Bump actions/stale from 9.1.0 to 10.0.0 (#24412) 3 people 2025-09-09 03:11:20 +00:00
• 13b89bd823 [doc] update vllm serve cli args documentation (#24329) cjackal 2025-09-09 12:07:58 +09:00
• 22a0070530 Bump actions/setup-python from 5.4.0 to 6.0.0 (#24414) 3 people 2025-09-09 02:54:58 +00:00
• 170129eb28 [gpt-oss] Harmony changes with container tool support (#23386) 5 people 2025-09-08 19:03:50 -07:00
• 955c624915 [Bugfix][Wide EP] Fix redundant work when using DeepEP, TP Attn, and EP MoE (#24134) Tyler Michael Smith 2025-09-08 22:01:51 -04:00
• 4f87abdcc6 Update reviewers for modelopt related files (#24468) Zhiyu 2025-09-08 18:53:13 -07:00
• 6910b56da2 [CI] Add nightly multiarch manifests to dockerhub (#24102) Sahithi ChigurupatiandSimon Mo 2025-09-08 18:18:09 -07:00
• e10fef0883 [Hardware][IBM Z] Fix Outlines Core issue for s390x (#24034) R3hankhan 2025-09-09 05:20:34 +05:30
• e680723eba [Bugfix] Disable the statslogger if the api_server_count is greater than 1 (#22227) ChaunceyandNick Hill 2025-09-09 06:28:03 +08:00
• 620db1fc58 [Attention] FlashAttention MLA cudagraph support (#23958) Matthew BonanniandRobert Shaw 2025-09-08 15:05:26 -07:00
• 41183c1fe0 [Spec Decode] Fix offline spec_decode.py (#24257) Ekagra RanjanandRoger Wang 2025-09-08 16:44:13 -04:00
• 43d9ad03ba [Model loader]: support multi-thread model weight loading (#23928) Yang KaiyongandSimon Mo 2025-09-09 02:49:39 +08:00
• 7be141b2c5 [CI] Enable encoder model compilation test (#24442) Jiangyun Zhu 2025-09-09 02:48:06 +08:00
• 8d7f39b48c [Model] Remove quantized mixtral (#24437) Jee Jee Li 2025-09-09 02:02:14 +08:00
• cd08636926 [Spec Decode][Benchmark] Add Blitzedit dataset (#23605) Ekagra RanjanandRoger Wang 2025-09-08 13:32:52 -04:00
• 3feeeb9fea [Spec Decode][Benchmark] Add Spec Bench Dataset for benchmarking (#23563) Ekagra Ranjan 2025-09-08 13:32:42 -04:00
• 6f4a82f8b5 [Model] Enable BNB support for qwen2_5_omni_thinker (#24420) Jee Jee Li 2025-09-09 00:37:08 +08:00
• c44797a4d6 [Docs]add eplb_config param use docs (#24213) rongfu.leng 2025-09-09 00:36:57 +08:00
• 55be93baf5 [Doc]: fix 2 hyperlinks leading to Ray site after they changed Ray's doc structure (#24438) Didier DurandandHarry Mellor 2025-09-08 18:36:54 +02:00
• 717fc00e98 [Docs] Move feature compatibility tables to README (#24431) Harry Mellor 2025-09-08 14:45:14 +01:00
• 01dfb5e982 [Frontend] User-provided uuids for medias in chat. (RFC #22044) (#23449) 4 people 2025-09-08 06:42:20 -07:00
• 03dd652c16 Move KVEventsConfig from config/__init__.py to config/kv_events.py (#24433) Harry Mellor 2025-09-08 14:41:27 +01:00
• 9cd76b71ab [Misc] Terratorch related fixes (#24337) Christian PintoandCyrus Leung 2025-09-08 15:40:26 +02:00
• e041314184 [Bugfix] Fix mamba2 prefill chunking (#23279) tomeras91andgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-08 14:42:41 +03:00
• 5e537f45b4 [Bugfix] Fix get_quant_config when using modelscope (#24421) Li Wang 2025-09-08 19:03:02 +08:00
• c2a8b08fcd [Doc] Fix issues in integrations/llamastack.md (#24428) Michael Yao 2025-09-08 17:28:32 +08:00
• f4962a6d55 [Doc]: fix typos in Python comments (#24417) Didier Durand 2025-09-08 09:22:16 +02:00
• 2f0b833a05 [Docs] Fix a tip indentation and typo (#24419) Michael Yao 2025-09-08 15:19:40 +08:00
• 425b04b8f4 [gpt-oss][Responses API] Fix the function call id format (#24409) Chauncey 2025-09-08 14:49:52 +08:00
• 60f0843ef8 [Model] Remove unnecessary CUDA sync of Qwen2VL image and video preprocess (#24334) Chatcharin SangbutsarakumandRoger Wang 2025-09-08 13:11:12 +07:00
• 8a46602606 [Model] Remove unnecessary CUDA sync of GLM-4.1V image and video preprocess (#24332) Chatcharin SangbutsarakumandRoger Wang 2025-09-08 13:10:54 +07:00
• 61aa4b2901 [P/D] Add a shutdown method to the Connector API (#22699) Chauncey 2025-09-08 14:07:00 +08:00
• 8c892b1831 [Doc] Fix UTF-8 encoding issues in documentation generation on Windows (#24361) Al-Ekram Elahee Hridoyandalekramelaheehridoy 2025-09-07 23:33:52 -06:00
• 3bca396f79 [CI/Build] Fix local image inputs in test_pixtral.py (#24401) Chenheli HuaandRoger Wang 2025-09-07 20:31:35 -07:00
• 3a3e91bdfe [CI/Build] Disable flaky test_structured_output tests (#24404) 22quinn 2025-09-07 19:51:59 -07:00
• b3d7e3c845 [Sampler] Support returning all prompt logprobs (#23868) 3 people 2025-09-07 19:34:31 -07:00
• 67841317d1 [xpu] upgrade ipex/python3.12 for xpu (#23830) Yan Ma 2025-09-08 10:07:16 +08:00
• 86173ad593 [Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385) Ming Yangandyoukaichao 2025-09-07 18:27:12 -07:00
• 795b6951cd Add @luccafong to codeowner for spec decode (#24397) Lucia Fang 2025-09-07 17:30:27 -07:00
• 2e5d21378d Skip MM Encoder for non-first PP ranks (#24387) Woosuk Kwon 2025-09-07 09:38:35 -07:00
• 0661cb9df3 Add renderer-based prompt processing for embedding and classification endpoints (#24356) Flora Feng 2025-09-07 01:26:48 -07:00
• 105d3d62ef [TPU] Remove TopKTopPSampler dependency for TPU sampler (#24391) Woosuk Kwon 2025-09-07 01:12:36 -07:00
• 62f66be1f7 [Bugfix] Fix Qwen3-coder moe tuned config (#24072) Jee Jee Li 2025-09-07 13:19:46 +08:00
• 81c53ef55c [Misc] collect flashinfer version in collect_env.py (#24378) Ye (Charlotte) Qi 2025-09-06 20:30:41 -07:00
• 75334956c2 QWEN3 Thinking Fused MoE kernels Optimization configs (#24330) Saman A. Pour 2025-09-06 20:18:54 -07:00
• 77aec83b8c [Benchmark] add benchmark for custom activation op (#23908) Jiangyun ZhuandLuka Govedič 2025-09-07 11:12:05 +08:00
• e67597545b [CI][Fix] deterministic seed for flaky CI runs on structured outputs (#24380) Aaron Pham 2025-09-06 23:10:40 -04:00
• 37a6fa95fd Migrate Qwen2 inputs to TensorSchema (#23475) Benji Beckandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-06 20:07:31 -07:00
• 558f0907dc [attention][DCP] use AttentionImpl.need_to_return_lse_for_decode (#24372) youkaichao 2025-09-07 09:18:59 +08:00
• 4172235ab7 [V0 deprecation] Deprecate V0 Neuron backend (#21159) Woosuk Kwon 2025-09-06 16:15:18 -07:00
• 848562bd49 break execute_model in gpu_model_runner into sub-functions for custom scopes (#24265) Bangsheng TangandBangsheng Tang 2025-09-06 14:02:47 -07:00
• e68dc2f014 [Bugfix] Fix unstable silu_mul+nvfp4 quant fusion test (#24370) elvischenv 2025-09-07 04:39:34 +08:00
• a3645ed94d [Frontend][Responses API] Support reporting tool output tokens and fix reasoning token count (#24285) Ye (Charlotte) Qi 2025-09-06 13:27:15 -07:00
• fb691ee4e7 [Fix] [gpt-oss] fix non-tool calling path for chat completion (#24324) Aaron Pham 2025-09-06 15:10:32 -04:00
• 6024d115cd Lora bias(enable_lora_bias) deprecate warning (#24339) Ashwin PhadkeandJee Jee Li 2025-09-06 22:12:19 +05:30
• 7555d6b34a [Bugfix] Fix test_mixtral_moe (#24371) Jee Jee Li 2025-09-07 00:32:03 +08:00
• 00a4e56d8d [Bugfix] Fix broken deepseek fp8 TP weights loading (#24367) Isotr0py 2025-09-07 00:23:12 +08:00
• 0eadaeff7e [Bugfix] Avoid uninitialized usage of azp_val when AZP is false. (#24335) mohankku 2025-09-06 08:17:03 -07:00
• 0077c8634e Add @benchislett to codeowner for spec decode and structured outputs (#24362) Benjamin Chislett 2025-09-06 10:03:35 -04:00
• b121ca22ad [CI] Disable flaky structured output test from CI (#24366) Roger Wang 2025-09-06 06:31:56 -07:00
• eddaafc1c7 [Multimodal] Improve max video embedding length estimation in V1 (#24312) Roger WangandRoger Wang 2025-09-06 02:33:19 -07:00
• 305a1cc0d2 refactor: Turn GPUModelRunner.inputs_embeds to a CpuGpuBuffer (#24345) Andrew Sansom 2025-09-06 01:01:23 -05:00
• 6d6c6b05d3 [New Model]: google/embeddinggemma-300m (#24318) wang.yuqi 2025-09-06 13:58:36 +08:00
• 53b19ccdd5 [Core] Allow disabling TP sharding for parallel Linear layer (#23024) Isotr0pyandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-09-06 13:53:58 +08:00
• 6432739ef1 [Bugfix] Catch and log invalid token ids in detokenizer (#24351) Nick Hill 2025-09-05 22:30:22 -07:00
• ac201a0eaf [Feature] Support Decode Context Parallel (DCP) for MLA (#23734) 3 people 2025-09-06 13:24:05 +08:00
• 3c529fc994 [KV Sharing] Raise error if using eagle with fast prefill (#24350) Yong Hoon Shin 2025-09-05 20:22:40 -07:00
• 35bf193864 [Doc]: fix typos in Python comments (#24294) Didier DurandandWentao Ye 2025-09-06 04:41:12 +02:00
• 35efa70297 Add @22quinn as code reviewer for RL related components (#24346) 22quinn 2025-09-05 18:56:15 -07:00
• cee182b297 [Perf][V1] Fully overlap model execution (#23569) Benjamin Chislett 2025-09-05 21:20:17 -04:00
• c954c6629c [CI] Add timeouts to tests (#24260) Rafael VasquezandNick Hill 2025-09-05 20:26:22 -04:00
• 9dfbeb41e5 [RFC] allow cancelation after shutdown in blocking collective_rpc (#23390) Shiyan Deng 2025-09-05 14:14:18 -07:00
• eedb2a2a10 [Bugfix] Fix silu_mul+quant fusion test (#24341) elvischenv 2025-09-06 04:13:42 +08:00
• 23a6c5280e [gpt-oss][Bugfix]Fix streamableparser for missing handling of certain token_ids (#24306) Chauncey 2025-09-06 01:26:00 +08:00
• 7812bcf278 [docs] add shenzhen meetup (#24326) youkaichao 2025-09-05 22:48:42 +08:00
• 006e7a34ae Adding int4 and int8 models for CPU benchmarking (#23709) Louie Tsai 2025-09-05 05:08:50 -07:00
• e599e2c65e [XPU][P/D] Add XPU support in NixlConnector (#22436) liuzhenweiandKunshang Ji 2025-09-05 12:03:12 +08:00
• c29fb540ff [gpt-oss] tool parser supports for /chat/completions [1/n] (#22386) Aaron PhamandSimon Mo 2025-09-04 23:39:12 -04:00
• 65e038931d [Frontend] Skip unnecessary detokenization when token_id is requested (#24236) Nicolò Lucchesi 2025-09-05 01:04:12 +02:00
• 886ccbe5ba [CI/Build] Reduce the number of redundant cases to test for LoRA (#24276) Zhuohan Li 2025-09-04 14:58:44 -07:00
• adc3ddb430 [Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for nvfp4 kernel source files (#23727) elvischenvandLuka Govedič 2025-09-05 05:25:45 +08:00
• 60b755cbcb [Misc] Have AsyncLLM custom_stat_loggers extend default logger list (#20952) Seiji EicherandNick Hill 2025-09-04 14:25:30 -07:00
• 482e52f56c QWEN3 Coder Fused MoE kernels Optimization configs (#24266) Saman A. Pour 2025-09-04 13:33:43 -07:00
• 78336a0c3e Upgrade FlashInfer to v0.3.0 (#24086) Po-Han Huang (NVIDIA)andSimon Mo 2025-09-05 00:49:20 +08:00
• 94866d7c93 [Misc] Slight improve deepgemm print (#24085) Jee Jee Li 2025-09-05 00:06:51 +08:00