Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 222f5b082a [CI/Build] Fix broken multimodal test (#10950) Cyrus LeungandGitHub 2024-12-06 18:41:23 +08:00
• b031a455a9 [torch.compile] add logging for compilation time (#10941) 3 people 2024-12-06 02:07:15 -08:00
• db87eb6c67 [torch.compile] use size tuning for specific sizes (#10933) youkaichaoandGitHub 2024-12-05 20:30:41 -08:00
• 9743d64e4e [ci][build] add tests for python only compilation (#10915) youkaichaoandGitHub 2024-12-05 08:54:47 -08:00
• a43065272f [Misc][Gaudi] Avoid torch.compile and enable lazy collectives (#10897) Konrad ZaworaandGitHub 2024-12-05 17:47:46 +01:00
• 998eeafe58 [CI/Build] Bump test transformers version (#10106) 3 people 2024-12-06 00:05:52 +08:00
• 571da8fc43 [Misc][LoRA] Clean up the function interface of Punica (#10917) Jee Jee LiandGitHub 2024-12-05 21:22:28 +08:00
• 39c89e71a8 [Misc] Update llama 3.2 template to support system prompt with images (#10901) Travis JohnsonandGitHub 2024-12-04 22:54:06 -07:00
• 1f958a7d52 [Bugfix] Fix BNB loader target_modules (#10720) Jee Jee LiandGitHub 2024-12-05 13:20:26 +08:00
• aa39a8e175 [Doc] Create a new "Usage" section (#10827) Cyrus LeungandGitHub 2024-12-05 11:19:35 +08:00
• 8d370e91cb [Bugfix] Fallback to outlines for complex json schemas (#10899) Michael GoinandGitHub 2024-12-04 22:14:06 -05:00
• 7883c2bbe7 [benchmark] Make H100 benchmark optional (#10908) Kevin H. LuuandGitHub 2024-12-04 17:02:17 -08:00
• 2a56e1264f [V1] Fix when max_model_len is not divisible by block_size (#10903) Woosuk KwonandGitHub 2024-12-04 16:54:05 -08:00
• e4c34c23de [CI/Build] improve python-only dev setup (#9621) 3 people 2024-12-04 22:48:13 +01:00
• 82eb5ea8f3 Benchmark serving structured output (#10880) 3 people 2024-12-04 15:28:21 -06:00
• 10398b4706 [Model] Consolidate ViTs attention implementation without mask (#10893) Isotr0pyandGitHub 2024-12-05 02:11:08 +08:00
• 01d079fd8e [LoRA] Change lora_tokenizers capacity (#10796) Xin YangandGitHub 2024-12-04 09:40:16 -08:00
• c92acb9693 [ci/build] Update vLLM postmerge ECR repo (#10887) Kevin H. LuuandGitHub 2024-12-04 01:01:20 -08:00
• 8db957ee3a [bugfix] fixed parameter “n” when set parameter “bestof” > 1 (#10854) jianzhengandGitHub 2024-12-04 16:48:22 +08:00
• c9ca4fce3f [ci/build] Job to build and push release image (#10877) Kevin H. LuuandGitHub 2024-12-03 23:02:40 -08:00
• fa2dea61df [ci/build] Change queue name for Release jobs (#10875) Kevin H. LuuandGitHub 2024-12-03 23:02:16 -08:00
• b5b647b084 Drop ROCm load format check (#10767) wangxiyuanandGitHub 2024-12-04 12:32:21 +08:00
• d2bd88b122 [CI/Build] Replace mean with torch.all in test_pynccl.py (#10876) Tyler Michael SmithandGitHub 2024-12-03 22:23:21 -05:00
• 381ac93bb5 [Benchmark] Benchmark structured output with datasets (#10557) 3 people 2024-12-03 18:21:06 -06:00
• a061fe601e [Build][Bugfix] Using the correct type hint (#10866) Gregory ShtrasbergandGitHub 2024-12-03 15:47:55 -05:00
• 7c32b6861e [Frontend] correctly record prefill and decode time metrics (#10853) tomeras91andGitHub 2024-12-03 21:13:31 +02:00
• 7090c27bb2 [Bugfix] Only require XGrammar on x86 (#10865) Michael GoinandGitHub 2024-12-03 13:32:21 -05:00
• 2f2cdc745a [MISC][XPU] quick fix for XPU CI (#10859) Yan MaandGitHub 2024-12-04 01:16:31 +08:00
• 3bc94cab69 [V1] VLM - Run the mm_mapper preprocessor in the frontend process (#10640) 4 people 2024-12-03 05:33:10 -05:00
• f6084f6324 [Speculative Decoding] Move indices to device before filtering output (#10850) 3 people 2024-12-03 17:01:39 +08:00
• 9323a3153b [Core][Performance] Add XGrammar support for guided decoding and set it as default (#10785) 3 people 2024-12-03 02:17:00 -05:00
• 3257d449fa [Misc] Remove deprecated names (#10817) Cyrus LeungandGitHub 2024-12-03 14:52:57 +08:00
• ef51831ee8 [Doc] Add github links for source code references (#10672) 3 people 2024-12-03 01:46:07 -05:00
• dc5ce861bf [torch.compile] remove compilation_context and simplify code (#10838) youkaichaoandGitHub 2024-12-02 22:19:02 -08:00
• 21fe7b481a [core][distributed] add pynccl broadcast (#10843) youkaichaoandGitHub 2024-12-02 20:53:23 -08:00
• a4cf256159 [Bugfix] Fix QKVParallelLinearWithShardedLora bias bug (#10844) Jee Jee LiandGitHub 2024-12-03 12:10:29 +08:00
• d746268e92 [Model] support bitsandbytes quantization with minicpm model (#10842) zixuanzhang226andGitHub 2024-12-02 19:06:41 -08:00
• 4433195ab7 [Bugfix] Prevent benchmark_throughput.py from using duplicated random prompts (#10753) Michael GoinandGitHub 2024-12-02 21:26:15 -05:00
• 4c05edb33a [Model] Add TP and BNB quantization support to LlavaMultiModalProjector (#10834) 3 people 2024-12-03 07:06:09 +08:00
• 9b14d978aa Fix openvino on GPU (#10793) Jani MonosesandGitHub 2024-12-02 20:52:19 +02:00
• 519cc6ca12 [Misc][XPU] Avoid torch compile for XPU platform (#10747) 3 people 2024-12-03 01:53:55 +08:00
• b45f0d7946 [Misc][LoRA] Move the implementation of lora bias to punica.py (#10829) Jee Jee LiandGitHub 2024-12-03 01:53:36 +08:00
• a4c4daf364 [misc] use out argument for flash attention (#10822) youkaichaoandGitHub 2024-12-02 02:50:10 -08:00
• e95f275f57 [CI/Build] Update mistral_common version for tests and docs (#10825) Cyrus LeungandGitHub 2024-12-02 18:26:10 +08:00
• ef31eabc68 [Model]: add some tests for aria model (#10770) 3 people 2024-12-02 13:36:36 +08:00
• 995a148575 [doc]Update config docstring (#10732) wangxiyuanandGitHub 2024-12-02 12:14:45 +08:00
• 63a164172d [misc] remove xverse modeling file (#10814) youkaichaoandGitHub 2024-12-01 19:27:13 -08:00
• e25810ae29 Fill TorchSDPAAttentionMetadata seq_lens_field for prefill (#10799) Maximilien de BayserandGitHub 2024-12-01 23:05:32 -03:00
• 073a4bd1c0 [Kernel] Use out arg in flash_attn_varlen_func (#10811) Woosuk KwonandGitHub 2024-12-01 17:55:39 -08:00
• b7954776fd [core] Avoid metrics log noise when idle - include speculative decodi… (#10809) cdukandGitHub 2024-12-02 02:49:48 +01:00
• b18c9bbaba [Model] Add BNB support to Llava and Pixtral-HF (#10795) Isotr0pyandGitHub 2024-12-02 09:31:09 +08:00
• 0590ec3fd9 [Core] Implement disagg prefill by StatelessProcessGroup (#10502) Kuntai DuandGitHub 2024-12-01 19:01:00 -06:00
• c11f172187 [Misc] Adding MMMU-Pro vision dataset to serving benchmark (#10804) 4 people 2024-12-01 00:47:05 -08:00
• 169a0ff911 [doc] add warning about comparing hf and vllm outputs (#10805) youkaichaoandGitHub 2024-12-01 00:41:38 -08:00
• d2f058e76c [Misc] Rename embedding classes to pooling (#10801) Cyrus LeungandGitHub 2024-12-01 14:36:51 +08:00
• f877a7d12a [Misc] Improve type annotations for support_torch_compile (#10763) Cyrus LeungandGitHub 2024-12-01 09:48:35 +08:00
• 133707123e [Model] Replace embedding models with pooling adapter (#10769) Cyrus LeungandGitHub 2024-12-01 08:02:54 +08:00
• 7e4bbda573 [doc] format fix (#10789) wangxiyuanandGitHub 2024-11-30 19:38:40 +08:00
• e7cfc4ef4c [Interleaved ATTN] Support for Mistral-8B (#10591) 3 people 2024-11-30 08:45:50 +01:00
• 16ee07f22a [Model] Refactor Molmo weights loading to use AutoWeightsLoader (#10771) Isotr0pyandGitHub 2024-11-30 12:19:14 +08:00
• 40bc242579 [Bugfix] Fix OpenVino/Neuron driver_worker init (#10779) 3 people 2024-11-30 05:07:13 +01:00
• 661175bc82 [platform] Add verify_quantization in platform. (#10757) wangxiyuanandGitHub 2024-11-29 23:22:21 +08:00
• 3132aac043 [Bugfix] Fix Idefics3 bug (#10778) Jee Jee LiandGitHub 2024-11-29 21:56:46 +08:00
• c82b432d4a [Misc] typo find in sampling_metadata.py (#10740) wang.yuqiandGitHub 2024-11-29 13:17:57 +08:00
• fa6ecb9aa7 [Model] Clean up MiniCPMV (#10751) Cyrus LeungandGitHub 2024-11-29 12:47:06 +08:00
• c83919c7a6 [Model] Add Internlm2 LoRA support (#5064) Isotr0pyandGitHub 2024-11-29 01:29:04 +08:00
• 98f47f2a40 [V1] Optimize the CPU overheads in FlashAttention custom op (#10733) Woosuk KwonandGitHub 2024-11-28 09:01:02 -08:00
• 8c1e77fb58 [Kernel] Update vllm-flash-attn version to reduce CPU overheads (#10742) Woosuk KwonandGitHub 2024-11-28 08:31:28 -08:00
• 5fc5ce0fe4 [Model] Added GLM-4 series hf format model support vllm==0.6.4 (#10561) 4 people 2024-11-28 22:53:31 +08:00
• 3ed5e73146 [TPU] Update requirements-tpu (#10726) Richard LiuandGitHub 2024-11-28 02:30:48 -08:00
• 9a8bff0285 [Kernel] Update vllm-flash-attn version (#10736) Woosuk KwonandGitHub 2024-11-28 02:25:59 -08:00
• a79b122400 [V1] Do not allocate beyond the max_model_len (#10730) Woosuk KwonandGitHub 2024-11-28 00:13:15 -08:00
• d9b4b3f069 [Bug][CLI] Allow users to disable prefix caching explicitly (#10724) Ricky XuandGitHub 2024-11-27 23:59:28 -08:00
• 278be671a3 [Doc] Update model in arch_overview.rst to match comment (#10701) 罗泽轩andGitHub 2024-11-28 15:58:39 +08:00
• 70dc14fbd0 [Model] support bitsandbytes quantization with minicpm3 model (#10682) zixuanzhang226andGitHub 2024-11-27 23:58:02 -08:00
• cb4e1c3f3a [misc] upgrade filelock version (#10731) youkaichaoandGitHub 2024-11-27 19:54:58 -08:00
• 395b1c7454 [Frontend] don't block event loop in tokenization (preprocess) in OpenAI compatible server (#10635) tomeras91andGitHub 2024-11-27 23:21:10 +02:00
• 9b4b150395 [Bugfix] Ignore lm_head when loading embedding models (#10719) Cyrus LeungandGitHub 2024-11-28 03:05:29 +08:00
• 197b4484a3 [Bugfix][Mamba] Fix Multistep on Mamba-like models (#10705) Mor ZusmanandGitHub 2024-11-27 21:02:27 +02:00
• b98c62ba49 [Bugfix] Fix GGUF inference with FP16 unquantized checkpoint (#10675) Isotr0pyandGitHub 2024-11-28 02:43:17 +08:00
• c411def234 [torch.compile] fix shape specialization (#10722) youkaichaoandGitHub 2024-11-27 10:16:10 -08:00
• 308cc5e21e [ci] fix slow tests (#10698) youkaichaoandGitHub 2024-11-27 09:26:14 -08:00
• 9e0a147d50 [V1] Update interface for mistral-format Pixtral (#10703) Roger WangandGitHub 2024-11-27 04:26:27 -08:00
• 418cb3b93f [Bugfix][Hardware][CPU] Fix intel-omp version to avoid segfault (#10700) Li, JiangandGitHub 2024-11-27 19:55:38 +08:00
• 1209261e93 [Model] Support telechat2 (#10311) 4 people 2024-11-27 19:32:35 +08:00
• e2251109c7 [Kernel] Remove if-else with identical branches in marlin 2:4 (#10687) Tyler Michael SmithandGitHub 2024-11-27 01:55:32 -05:00
• 15cc2a9f1a [Misc]Further reduce BNB static variable (#10597) Jee Jee LiandGitHub 2024-11-27 14:54:12 +08:00
• e85250b1d1 [Hardware][Gaudi]add get_name method for HPUAttentionBackend (#10667) Kunshang JiandGitHub 2024-11-27 14:49:40 +08:00
• cfb3bf25fb [bugfix] fix the default value of llm_int8_threshold in BitsAndBytesConfig (#10657) yansh97andGitHub 2024-11-27 13:55:23 +08:00
• 1bf905ddaa [Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. (#10198) jeongin601andGitHub 2024-11-27 14:07:30 +09:00
• 0a4d968500 [V1] Update interface for idefics3 (#10680) Roger WangandGitHub 2024-11-26 18:04:01 -08:00
• 0a71900bc9 Remove hard-dependencies of Speculative decode to CUDA workers (#10587) Chendi.XueandGitHub 2024-11-26 19:57:11 -06:00
• 2f0a0a17a4 [V1] Refactor model executable interface for multimodal models (#10570) Roger WangandGitHub 2024-11-26 12:46:11 -08:00
• 7576cd38df [Bugfix] Check bnb_4bit_quant_storage for bitsandbytes (#10642) Michael GoinandGitHub 2024-11-26 15:29:00 -05:00
• 9a99273b48 [Bugfix] Fix using -O[0,3] with LLM entrypoint (#10677) Michael GoinandGitHub 2024-11-26 13:44:01 -05:00
• f5792c7c4a [Hardware][NVIDIA] Add non-NVML CUDA mode for Jetson (#9735) Conroy CheersandGitHub 2024-11-27 05:26:28 +11:00
• db66e018ea [Bugfix] Fix for Spec model TP + Chunked Prefill (#10232) 3 people 2024-11-26 09:11:16 -08:00
• 1f6584ee85 [V1] Enable profile for LLMEngine (#10665) Kunshang JiandGitHub 2024-11-26 18:36:45 +08:00
• 334d64d1e8 [ci] add vllm_test_utils (#10659) youkaichaoandGitHub 2024-11-26 00:20:04 -08:00
• 940635343a [Misc] Remove outdated init protocols (#10655) Cyrus LeungandGitHub 2024-11-26 14:55:00 +08:00