Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 5f6d10c14c [CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722) Michael GoinandGitHub 2024-05-22 03:18:41 -04:00
• 9b9a10d6cb [Frontend] Dynamic RoPE scaling (#4638) sasha0552andGitHub 2024-05-22 05:32:35 +00:00
• 99eff67ba9 [Bugfix][Kernel] Add head size check for attention backend selection (#4944) Isotr0pyandGitHub 2024-05-22 03:33:25 +08:00
• 14772eeb8e [Bugfix] Fix flag name for max_seq_len_to_capture (#4935) Kante YinandGitHub 2024-05-22 00:30:52 +08:00
• 757b62c495 [CI/Build] Codespell ignore build/ directory (#4945) Michael GoinandGitHub 2024-05-21 12:06:10 -04:00
• e941f88584 [Docs] Add acknowledgment for sponsors (#4925) Simon MoandGitHub 2024-05-21 00:17:25 -07:00
• f12c3b5b3d [Model] Add Phi-2 LoRA support (#4886) Isotr0pyandGitHub 2024-05-21 13:24:17 +08:00
• d130b573a0 [Model] add rope_scaling support for qwen2 (#4930) HUANG FeiandGitHub 2024-05-21 13:22:22 +08:00
• 65ae8c2c8f [Core] Fix scheduler considering "no LoRA" as "LoRA" (#4897) Antoni BaumandGitHub 2024-05-20 17:48:32 -07:00
• c3af44722c [Doc]Add documentation to benchmarking script when running TGI (#4920) Kuntai DuandGitHub 2024-05-20 13:16:57 -07:00
• 1937e29848 [Core] Sharded State Loader download from HF (#4889) Aurick QiaoandGitHub 2024-05-20 14:46:12 -04:00
• f0eecee610 [Bugfix] Fix dummy weight for fp8 (#4916) 3 people 2024-05-20 21:44:25 +03:00
• 943e72ca56 [Build/CI] Enabling AMD Entrypoints Test (#4834) 3 people 2024-05-20 13:29:28 -05:00
• 546a97ef69 [Misc]: allow user to specify port in distributed setting (#4914) Wenwei ZhangandGitHub 2024-05-21 01:45:06 +08:00
• da5a0b539d Remove marlin warning (#4918) Alexander MatveevandGitHub 2024-05-20 10:55:34 -04:00
• 6287537a0c [Model] LLaVA model refactor (#4910) Cyrus LeungandGitHub 2024-05-20 16:11:25 +08:00
• b57e6c5949 [Kernel] Add flash-attn back (#4907) Woosuk KwonandGitHub 2024-05-19 18:11:30 -07:00
• 27ce85476e [Kernel] Add marlin_24 unit tests (#4901) Alexander MatveevandGitHub 2024-05-19 11:37:34 -04:00
• f68470e803 [Bugfix][Model] Add base class for vision-language models (#4809) Cyrus LeungandGitHub 2024-05-19 15:13:33 +08:00
• 2e9a2227ec [Lora] Support long context lora (#4787) SangBin ChoandGitHub 2024-05-18 16:05:23 +09:00
• c0724fc915 [ROCm][Hardware][AMD] Adding Navi21 to fallback to naive attention if Triton is not used (#4658) alexeykondratandGitHub 2024-05-18 01:09:11 -04:00
• 86b45ae065 [Bugfix] Relax tiktoken to >= 0.6.0 (#4890) Michael GoinandGitHub 2024-05-17 14:58:52 -04:00
• c5711ef985 [Doc] Update Ray Data distributed offline inference example (#4871) Antoni BaumandGitHub 2024-05-17 10:52:11 -07:00
• 48d5985a08 Sync huggingface modifications of qwen Moe model (#4774) eigenLiuandGitHub 2024-05-18 00:43:19 +08:00
• 33e0823de5 [Bugfix] fix rope error when load models with different dtypes (#4835) Jinzhen LinandGitHub 2024-05-17 17:43:34 +08:00
• 26148120b3 [Build/CI] Extending the set of AMD tests with Regression, Basic Correctness, Distributed, Engine, Llava Tests (#4797) Alexei-V-Ivanov-AMDandGitHub 2024-05-16 22:58:25 -05:00
• 0150a10630 [Frontend] OpenAI API server: Do not add bos token by default when encoding (#4688) bofeng huangandGitHub 2024-05-17 03:47:22 +02:00
• 8e7fb5d43a Support to serve vLLM on Kubernetes with LWS (#4829) Kante YinandGitHub 2024-05-17 07:37:29 +08:00
• 9a31a817a8 [Bugfix] Fix FP8 KV cache support (#4869) Woosuk KwonandGitHub 2024-05-16 15:42:29 -07:00
• 2060e93659 [Kernel] Add w8a8 CUTLASS kernels (#4749) Tyler Michael SmithandGitHub 2024-05-16 18:32:50 -04:00
• 8435b207af [Kernel] Add punica dimension for Qwen1.5-32B LoRA (#4850) 3 people 2024-05-17 02:16:09 +08:00
• 10fa9eea21 [Misc] remove old comments (#4866) youkaichaoandGitHub 2024-05-16 11:07:41 -07:00
• e08188081b [Core][Distributed] remove graph mode function (#4818) youkaichaoandGitHub 2024-05-16 10:59:52 -07:00
• b5853f9963 [ROCm][AMD][Bugfix] adding a missing triton autotune config (#4845) Hongxia YangandGitHub 2024-05-16 13:46:52 -04:00
• f09edd8a25 Add JSON output support for benchmark_latency and benchmark_throughput (#4848) Simon MoandGitHub 2024-05-16 10:02:56 -07:00
• 6979ade384 Add GPTQ Marlin 2:4 sparse structured support (#4790) 3 people 2024-05-16 12:56:15 -04:00
• 9216b9cc38 [Bugfix] Bypass authorization API token for preflight requests (#4862) Pierre DulacandGitHub 2024-05-16 18:42:21 +02:00
• 5e0391c040 [Frontend] Separate OpenAI Batch Runner usage from API Server (#4851) Alex WuandGitHub 2024-05-16 11:42:41 -04:00
• dbc0754ddf [docs] Fix typo in examples filename openi -> openai (#4864) Alex WuandGitHub 2024-05-16 11:42:17 -04:00
• 99caa49106 [Kernel] add bfloat16 support for gptq marlin kernel (#4788) Jinzhen LinandGitHub 2024-05-16 21:55:29 +08:00
• 5c342570d7 Add marlin unit tests and marlin benchmark script (#4815) alexm-nmandGitHub 2024-05-16 09:36:49 -04:00
• 973617ae02 [Speculative decoding][Re-take] Enable TP>1 speculative decoding (#4840) 4 people 2024-05-16 00:53:51 -07:00
• 30e754390c [Core] Implement sharded state loader (#4690) 3 people 2024-05-16 01:11:54 -04:00
• 52f8107cf2 [Frontend] Support OpenAI batch file format (#4794) 3 people 2024-05-15 19:13:36 -04:00
• fc0d9dfc3a [Frontend] Re-enable custom roles in Chat Completions API (#4758) Cyrus LeungandGitHub 2024-05-16 05:58:46 +08:00
• 361c461a12 [Doc] Highlight the fourth meetup in the README (#4842) Zhuohan LiandGitHub 2024-05-15 11:38:49 -07:00
• a5675d348b [Bugfix] Properly set distributed_executor_backend in ParallelConfig (#4816) zifeitongandGitHub 2024-05-15 07:22:09 -07:00
• e9cdd2b1e2 [CI/Build] Further decouple HuggingFace implementation from ours during tests (#4166) Cyrus LeungandGitHub 2024-05-15 14:38:40 +08:00
• 65bf2ac165 [Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681) SangBin ChoandGitHub 2024-05-15 14:00:10 +09:00
• 8a7cc254a0 Revert "[Kernel] Use flash-attn for decoding (#3648)" (#4820) SangBin ChoandGitHub 2024-05-15 11:52:45 +09:00
• 29bc01bf3b Add 4th meetup announcement to readme (#4817) Simon MoandGitHub 2024-05-14 15:33:06 -07:00
• 676a99982f [Core] Add MultiprocessingGPUExecutor (#4539) 3 people 2024-05-14 10:38:59 -07:00
• dc72402b57 [Bugfix][Doc] Fix CI failure in docs (#4804) Cyrus LeungandGitHub 2024-05-15 00:57:08 +08:00
• ccb63a8245 [Core][Hash][Automatic Prefix caching] Accelerating the hashing function by avoiding deep copies (#4696) Kuntai DuandGitHub 2024-05-14 05:34:33 -07:00
• c579b750a0 [Doc] Add meetups to the doc (#4798) Zhuohan LiandGitHub 2024-05-13 18:48:00 -07:00
• 4bfa7e7f75 [Doc] Add API reference for offline inference (#4710) Cyrus LeungandGitHub 2024-05-14 08:47:42 +08:00
• ac1fbf7fd2 [Doc] Shorten README by removing supported model list (#4796) Zhuohan LiandGitHub 2024-05-13 16:23:54 -07:00
• 33d3914b1e [Bugfix] Fix dynamic FP8 quantization for Mixtral (#4793) Philipp MoritzandGitHub 2024-05-13 16:00:27 -07:00
• 1356df53bd [Kernel] Use flash-attn for decoding (#3648) 4 people 2024-05-13 15:50:33 -07:00
• ce532ff45c [Speculative decoding] Improve n-gram efficiency (#4724) Cody YuandGitHub 2024-05-13 15:00:13 -07:00
• 8bc68e198c [Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update tensorizer to version 2.9.0 (#4208) Sanger SteelandGitHub 2024-05-13 17:57:07 -04:00
• 0fca3cdcf2 [Misc] Enhance attention selector (#4751) Woosuk KwonandGitHub 2024-05-13 10:47:25 -07:00
• e7c46b9527 [Scheduler] Warning upon preemption and Swapping (#4647) 3 people 2024-05-13 23:50:44 +09:00
• 350f9e107f [CI/Build] Move test_utils.py to tests/utils.py (#4425) Cyrus LeungandGitHub 2024-05-13 22:50:09 +08:00
• 702bee461f [Core][Distributed] refactor custom allreduce to support multiple tp groups (#4754) youkaichaoandGitHub 2024-05-12 17:47:59 -07:00
• a7be4d0072 [CORE] Improvement in ranks code (#4718) Swapnil ParekhandGitHub 2024-05-12 20:47:47 -04:00
• a709e87a4f [CI/Build] Tweak Marlin Nondeterminism Issues (#4713) Robert ShawandGitHub 2024-05-12 20:46:31 -04:00
• 6eaccb7353 [Model] Add support for IBM Granite Code models (#4636) Yikang ShenandGitHub 2024-05-12 00:27:24 -04:00
• e254497b66 [Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734) Chang SuandGitHub 2024-05-11 11:30:37 -07:00
• 4e12131089 [Core][Test] fix function name typo in custom allreduce (#4750) youkaichaoandGitHub 2024-05-10 15:14:40 -07:00
• fcc2994be6 [CI] Nits for bad initialization of SeqGroup in testing (#4748) Robert ShawandGitHub 2024-05-10 16:01:01 -06:00
• 2e7796f2cf [Speculative decoding] CUDA graph support (#4295) 3 people 2024-05-11 02:36:25 +09:00
• 706588a77d [Bugfix] Fix CLI arguments in OpenAI server docs (#4729) Allen.DouandGitHub 2024-05-10 23:00:56 +08:00
• 6a0f617210 [Core] Fix circular reference which leaked llm instance in local dev env (#4737) SangBin ChoandGitHub 2024-05-10 23:54:32 +09:00
• dac6a3f6ed [Misc] Apply a couple g++ cleanups (#4719) Steve GrubbandGitHub 2024-05-10 09:37:05 -04:00
• 64b77dfd7e [Core]fix type annotation for swap_blocks (#4726) Kunshang JiandGitHub 2024-05-10 20:52:48 +08:00
• 51d4094fda chunked-prefill-doc-syntax (#4603) 3 people 2024-05-09 22:13:23 -07:00
• e965d46184 [Misc] Keep only one implementation of the create_dummy_prompt function. (#4716) Allen.DouandGitHub 2024-05-10 12:42:38 +08:00
• 208b71bcc1 [Core][Distributed] refactor pynccl (#4591) youkaichaoandGitHub 2024-05-09 19:48:43 -07:00
• c833101740 [Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (#4535) Cody YuandGitHub 2024-05-09 17:04:17 -07:00
• 379da6dcb5 [Kernel] [FP8] Improve FP8 linear layer performance (#4691) Philipp MoritzandGitHub 2024-05-09 16:38:07 -07:00
• ebce310b74 [Model] Snowflake arctic model implementation (#4652) 7 people 2024-05-09 15:37:14 -07:00
• be0c5180ac [Bugfix] Add logs for all model dtype casting (#4717) Michael GoinandGitHub 2024-05-09 14:36:25 -04:00
• cea64430f6 [Bugfix] Update grafana.json (#4711) Robert ShawandGitHub 2024-05-09 11:10:13 -06:00
• a3c124570a [Bugfix] Fix CLI arguments in OpenAI server docs (#4709) Cyrus LeungandGitHub 2024-05-10 00:53:14 +08:00
• ff5abcd746 [ROCm] Add support for Punica kernels on AMD GPUs (#3140) 3 people 2024-05-10 00:19:50 +08:00
• 0ee535b294 [Misc] Set block size at initialization & Fix test_model_runner (#4705) Woosuk KwonandGitHub 2024-05-09 09:04:59 -07:00
• 190bc838e1 [Misc] Remove unnecessary ModelRunner imports (#4703) Woosuk KwonandGitHub 2024-05-09 00:17:17 -07:00
• f12b20decc [Frontend] Move async logic outside of constructor (#4674) Cyrus LeungandGitHub 2024-05-09 13:48:33 +08:00
• 16bc0a098f [Frontend] add tok/s speed metric to llm class when using tqdm (#4400) 3 people 2024-05-09 08:02:31 +03:00
• e288df0632 [Bugfix] Fine-tune gptq_marlin configs to be more similar to marlin (#4626) alexm-nmandGitHub 2024-05-08 20:14:31 -04:00
• 8b9241be3a [Speculative decoding] [Bugfix] Fix overallocation in ngram + spec logprobs (#4672) Cade DanielandGitHub 2024-05-08 16:24:46 -07:00
• f942efb5a3 [Dynamic Spec Decoding] Auto-disable by the running queue size (#4592) 3 people 2024-05-08 14:44:00 -07:00
• 89579a201f [Misc] Use vllm-flash-attn instead of flash-attn (#4686) Woosuk KwonandGitHub 2024-05-08 13:15:34 -07:00
• 230c4b38c1 [CI/Test] fix swap test for multi gpu (#4689) youkaichaoandGitHub 2024-05-08 13:14:02 -07:00
• 20cfcdec99 [Core][Optimization] change python dict to pytorch tensor for blocks to swap (#4659) youkaichaoandGitHub 2024-05-08 12:07:05 -07:00
• ad932a221d [Core] Faster startup for LoRA enabled models (#4634) Antoni BaumandGitHub 2024-05-08 10:33:18 -07:00
• 5510cf0e8a [Misc] Add get_name method to attention backends (#4685) Woosuk KwonandGitHub 2024-05-08 09:59:31 -07:00
• 0f9a6e3d22 [Bugfix][Kernel] allow non-power-of-2 for prefix prefill with alibi (#4573) DefTruthandGitHub 2024-05-09 00:19:58 +08:00
• f6a593093a [CI] Make mistral tests pass (#4596) SangBin ChoandGitHub 2024-05-09 00:44:35 +09:00