Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• ee378f3d49 [Model] support modernbert (#16648) xsankand唯勤 2025-04-16 20:30:15 +08:00
• e82ee40de3 [Bugfix][Kernel] fix potential cuda graph broken for merge_attn_states kernel (#16693) DefTruth 2025-04-16 18:31:39 +08:00
• facbe2a114 [Doc] Improve OOM troubleshooting (#16704) Cyrus Leung 2025-04-16 18:29:48 +08:00
• 7168920491 [Misc] refactor examples series (#16708) Reidandreidliu41 2025-04-16 18:16:36 +08:00
• 21378a2323 [CI] Cleanup additional_dependencies: [toml] for pre-commit yapf hook (#16405) Kay Yan 2025-04-16 18:05:31 +08:00
• 976711d9db [V1][Structured Output] Move xgrammar related utils to backend_xgrammar.py (#16578) Shanshan Shen 2025-04-16 17:01:36 +08:00
• 44fa4d556c [ROCM] Bind triton version to 3.2 in requirements-built.txt (#16664) Sage Moore 2025-04-15 23:05:28 -07:00
• 3ac98edcb1 [Feature] add model aware kv ops helper (#16020) billishyahao 2025-04-16 14:00:43 +08:00
• 966c742ed2 Disable remote caching when calling compile_fx (#16611) Richard Zou 2025-04-16 01:18:28 -04:00
• 0d7d05f4b6 [Misc] Modify LRUCache touch (#16689) Jee Jee Li 2025-04-16 12:51:38 +08:00
• 96bb8aa68b [Bugfix] fix gpu docker image mis benchmarks dir (#16628) rongfu.leng 2025-04-16 12:21:14 +08:00
• 3badb0213b [Model] Add PLaMo2 (#14323) 4 people 2025-04-16 11:31:30 +09:00
• fdcb850f14 [Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server (#10546) Angky WilliamandAngky William 2025-04-15 15:31:38 -07:00
• 54a66e5fee [Misc] Update compressed-tensors WNA16 to support zero-points (#14211) Dipika Sikka 2025-04-15 09:33:51 -04:00
• 280d62b8a2 [Kernel] Remove redundant Exp calculations (#16123) DefTruth 2025-04-15 20:58:37 +08:00
• 1666e66443 Add "/server_info" endpoint in api_server to retrieve the vllm_config.  (#16572) Xihui Cang 2025-04-15 19:50:38 +08:00
• 1575c1701a [CI/Build] Fix LoRA OOM (#16624) Jee Jee Li 2025-04-15 16:38:19 +08:00
• 6ae996a873 [Misc] refactor argument parsing in examples (#16635) Reidandreidliu41 2025-04-15 16:05:30 +08:00
• b590adfdc1 Fix vLLM x torch.compile config caching (#16491) Richard Zou 2025-04-15 02:11:11 -04:00
• b4fe16c75b Add vllm bench [latency, throughput] CLI commands (#16508) Michael Goin 2025-04-15 00:10:35 -06:00
• bc5dd4f669 [Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) (#16631) Pooya Davoodi 2025-04-14 23:09:58 -07:00
• dbb036cf61 [Bugfix] Fix tests/kernels/test_mamba_ssm_ssd.py (#16623) Tyler Michael Smith 2025-04-15 01:35:38 -04:00
• 70e7ed841d [BugFix]: Update minimum pyzmq version (#16549) Taneem Ibrahimandmgoin 2025-04-14 22:06:03 -05:00
• d06ba4ed3f [Kernel] moe wna16 marlin kernel (#14447) 3 people 2025-04-15 11:05:22 +08:00
• 6b40996ae8 [Core][Bugfix] Fix Offline MM Beam Search (#16390) Alex BrooksandCyrus Leung 2025-04-14 20:33:02 -06:00
• d2020acac7 config check sleep mode support oot platforms (#16562) Shuqiao Li 2025-04-15 07:31:50 +08:00
• 1eb3c2ed48 [DOC][TPU] Add core idea about avoiding recompilation after warmup (#16614) Chengji Yao 2025-04-14 14:56:06 -07:00
• c64ee87267 [Hardware][TPU] Add torchvision to tpu dependency file (#16616) Siyuan Liu 2025-04-14 14:50:46 -07:00
• b1308b84a3 [Model][VLM] Add Kimi-VL model support (#16387) courage17340 2025-04-15 05:41:48 +08:00
• 7b5ecf79bd s390x: Fix PyArrow build and add CPU test script for Buildkite CI (#16036) Nishan Acharya 2025-04-14 23:25:32 +05:30
• 9883a18859 Fix triton install condition on CPU (#16600) Harry Mellor 2025-04-14 18:06:01 +01:00
• b3f2fddd17 [TPU][V1] Fix exponential padding when max-num-batched-tokens is not a power of 2 (#16596) Nicolò Lucchesi 2025-04-14 19:01:05 +02:00
• aa29841ede [Bugfix] Multi-modal caches not acting like LRU caches (#16593) Cyrus Leung 2025-04-15 00:24:16 +08:00
• 6bf27affb6 [fix]: Dockerfile.ppc64le fixes for opencv-python and hf-xet (#16048) Md. Shafi Hussain 2025-04-14 21:38:39 +05:30
• 1dd23386ec [Misc] Update usage with mooncake lib for kv transfer (#16523) shangmingc 2025-04-14 19:31:37 +08:00
• 7cbfc10943 [Misc] refactor examples (#16563) Reidandreidliu41 2025-04-14 17:59:15 +08:00
• ce4ddd2d1a [Misc] remove warning if triton>=3.2.0 (#16553) DefTruth 2025-04-14 17:39:47 +08:00
• e51929ebca Improve configs - SchedulerConfig (#16533) Harry Mellor 2025-04-14 10:24:16 +01:00
• dc1b4a6f13 [Core][V0] Enable regex support with xgrammar (#13228) Russell Bryant 2025-04-13 22:13:38 -04:00
• 63d2705edb [Benchmark][Bugfix] Fix SonnetDataset default values in benchmark_throughput.py (#16556) Jennifer Zhao 2025-04-13 17:20:26 -07:00
• d085a44082 Enable PTPC FP8 for CompressedTensorsW8A8Fp8MoEMethod (triton fused_moe) (#16537) Michael Goin 2025-04-13 08:55:18 -06:00
• f49e5aff11 [V1][Spec Decode] KV cache slots for eagle heads (#16370) Lily Liu 2025-04-12 19:42:51 -07:00
• 6c11ecf8d3 [Bugfix] Validate logit biases to prevent out of vocab ids crashing engine (#16529) Ryan McConville 2025-04-12 21:19:19 +01:00
• 93e5f3c5fb [Perf] Optimize Preparing Inputs for GPU Model Runner (#16484) SnowCharmandNick Hill 2025-04-12 22:54:37 +08:00
• 70363bccfa Fix syntaxWarning: invalid escape sequence '\s' (#16532) Jie Fu (傅杰) 2025-04-12 22:39:42 +08:00
• 3cdc57669f [Misc] Delete redundant code (#16530) Jee Jee LiandIsotr0py 2025-04-12 19:21:37 +08:00
• 68bb122eb4 [MISC] Make GroupCoordinator compatible with out-of-tree devices (#16464) Huazhong Ji 2025-04-12 17:20:25 +08:00
• d9fc8cd9da [V1] Enable multi-input by default (#15799) Cyrus Leung 2025-04-12 16:52:39 +08:00
• f069f3ea74 [Misc] Openai transcription client example use same Whisper model (#16487) Nicolò Lucchesi 2025-04-12 09:27:03 +02:00
• c5bc0e7fcc [Misc] Update chat utils tests (#16520) Cyrus Leung 2025-04-12 14:48:43 +08:00
• 4a3a518722 fix: spelling (#16466) Tianer Zhou 2025-04-12 14:24:22 +08:00
• fbf722c6e6 [Frontend] support matryoshka representation / support embedding API dimensions (#16331) wang.yuqi 2025-04-12 14:23:10 +08:00
• e92d7085bf [Feature][V1] Add xgrammar to support minLength, maxLength with test (#16516) leon-seidel 2025-04-12 08:22:07 +02:00
• bd6028d6b0 Optimized topk for topk=1 (Llama-4) (#16512) Michael Goin 2025-04-12 00:21:08 -06:00
• 802329dee9 [Doc] Update Llama4 Model Names in Supported Models (#16509) Ye (Charlotte) Qi 2025-04-11 19:53:10 -07:00
• 41cc883c29 [BugFix] Handle non-contiguous tensors properly when serializing (#16492) Nick Hill 2025-04-11 17:54:06 -07:00
• 57504a4bcf [CI][Bugfix] Add mistral_tool_use to Ci (#16517) Michael Goin 2025-04-11 18:52:38 -06:00
• ed4792c990 [Doc] Fix link to vLLM blog (#16519) Yuan Tang 2025-04-11 20:39:23 -04:00
• 87b836ba77 Bugfix for PixtralHF models without spatial_merge_size (#16513) Michael Goin 2025-04-11 17:32:22 -06:00
• 56c76c2e0e [Bugfix] clean up duplicated code (#16485) rongfu.lengandGogs 2025-04-12 07:19:40 +08:00
• c09632a66c Update openai_compatible_server.md (#16507) Christian Sears 2025-04-11 18:54:58 -04:00
• a3bf8d4a2b [Kernel] Add tuned FusedMoE kernel config for Llama4 Scout, TP=8 on H100 (#16488) Yong Hoon Shin 2025-04-11 15:26:55 -07:00
• 16eda8c43a [Frontend] Added chat templates for LLaMa4 pythonic tool calling (#16463) Ye (Charlotte) QiandKai Wu 2025-04-11 15:26:17 -07:00
• cd77382ac1 Improve configs - LoadConfig (#16422) Harry Mellor 2025-04-11 21:27:27 +01:00
• 71b9cde010 [Bugfix] handle alignment of encoder_seq_lens in mllama.py (#14784) Travis Johnson 2025-04-11 13:59:50 -06:00
• 5285589f37 [Doc] Document InternVL3 support (#16495) Isotr0py 2025-04-12 03:41:09 +08:00
• f41647ee6b [Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel (#16366) Michael Goin 2025-04-11 11:54:08 -06:00
• 4d022cbc75 [TPU][V1] Make --disable_chunked_mm_input mandatory for serving MM models (#16483) Nicolò Lucchesi 2025-04-11 19:06:14 +02:00
• 70de35a881 Fix erroneous "model doesn't support compile" warning (#16486) Richard Zou 2025-04-11 12:24:36 -04:00
• 34b2cf3b33 [Hardware][Intel-Gaudi] Multi-step scheduling implementation for HPU (#12779) Tomasz Zielinski 2025-04-11 16:38:36 +02:00
• 9e90c9f73f [Bugfix] Fix bugs of running Quark quantized models (#16236) chaow-amd 2025-04-11 22:18:32 +08:00
• e9528f6dc6 [Kernel] support merge_attn_states CUDA kernel, 3x speedup (#16173) DefTruth 2025-04-11 20:50:50 +08:00
• 51baa9c333 Don't install triton on ppc64le platform (#16470) Harry Mellor 2025-04-11 11:11:00 +01:00
• 35e076b3a8 [Misc] update api_client example (#16459) Reidandreidliu41 2025-04-11 18:05:40 +08:00
• a26f59ccbc [Misc] Raise error for V1 not supporting Long LoRA. (#16415) Jee Jee Li 2025-04-11 16:51:20 +08:00
• aa3b3d76e0 Enforce valid max_num_batched_tokens when disable_chunked_mm_input=True (#16447) Michael Goin 2025-04-11 02:09:52 -06:00
• f7030df3be [Core][LoRA][1/N] Add LoRA for EncoderDecoderModelRunner (#15990) Jee Jee Li 2025-04-11 15:32:37 +08:00
• 905e91e9ac Revert "[Model] use AutoWeightsLoader for deepseek_v2, internlm2" (#16453) DefTruth 2025-04-11 14:44:22 +08:00
• f8f9c0ba62 [Bugfix] Don't set an upper bound on repetition penalty (#16403) Alex BrooksandNick Hill 2025-04-11 00:19:40 -06:00
• dda811021a [CPU][Bugfix] Fix CPU docker issues (#16454) Li, Jiang 2025-04-11 14:19:07 +08:00
• 93195146ea [Bugfix][VLM] Fix failing Phi-4-MM multi-images tests and add vision-speech test (#16424) Isotr0py 2025-04-11 12:57:16 +08:00
• ed37599544 Update supported_hardware.md for TPU INT8 (#16437) Michael Goin 2025-04-10 22:28:07 -06:00
• 99ef59cf7f [Llama4] Enable attention temperature tuning by default for long context (>32k) (#16439) Yong Hoon ShinandYe Qi 2025-04-10 21:26:07 -07:00
• d544d141ec update benchmark_serving_structured_output to include auto backend (#16438) Chenyaaang 2025-04-10 21:25:52 -07:00
• 3e397a9484 check input length of sonnet samples (#16423) Alexey Belyakov 2025-04-11 03:15:06 +01:00
• 268c325078 Fix range_ratio Bug in RandomDataset (#16126) WWW 2025-04-11 06:31:17 +08:00
• 3cc9af88ff [TPU][V1] Disable per-request seed/Generator (#16172) Nicolò Lucchesi 2025-04-10 23:05:44 +02:00
• 7cd0bd7212 [Bugfix] Fix output token length check logic (#16419) look 2025-04-11 04:16:48 +08:00
• 56d4aefa33 [VLM] Avoid unnecessary dummy multimodal data during processing (#16416) Cyrus Leung 2025-04-11 03:32:14 +08:00
• dd143ef541 [V1] Zero-copy tensor/ndarray serialization/transmission (#13790) Nick Hill 2025-04-10 12:23:14 -07:00
• daefed052c [Model] Reduce redundant computations in mamba2 blocks for Bamba-9B (#15423) Chih-Chieh YangandYu Chin Fabian Lim 2025-04-10 15:07:07 -04:00
• 5fbab20e02 [Bugfix] Fix bug when dataset is json (#15899) Chenyaaang 2025-04-10 11:35:41 -07:00
• e8224f3dca [V1][Spec Decode] Eagle Model loading (#16035) Lily Liu 2025-04-10 11:21:48 -07:00
• 9665313c39 [V1] Set structured output backend to auto by default (#15724) Russell Bryant 2025-04-10 13:53:26 -04:00
• 0c54fc7273 Improve configs - ParallelConfig (#16332) Harry Mellor 2025-04-10 18:34:37 +01:00
• c1b57855ec [TPU][V1] Use language_model interface for getting text backbone in MM (#16410) Nicolò Lucchesi 2025-04-10 19:32:04 +02:00
• 83b824c8b4 [VLM] Remove BaseProcessingInfo.get_mm_max_tokens_per_item (#16408) Cyrus Leung 2025-04-11 00:06:58 +08:00
• 7678fcd5b6 Fix the torch version parsing logic (#15857) Lu Fang 2025-04-10 07:37:47 -07:00
• 8661c0241d [CI] Add auto update workflow for Dockerfile graph (#11879) wineandchord 2025-04-10 21:43:05 +08:00
• ce8d6b75fc [doc] update the wrong link (#16401) Reidandreidliu41 2025-04-10 21:02:37 +08:00