Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 36729bac13 [Test] Test multiple attn backend for chunked prefill. (#4023) SangBin ChoandGitHub 2024-04-13 01:56:57 +09:00
• 7fd3949a0b [Frontend][Core] Move merge_async_iterators to utils (#4026) Cyrus LeungandGitHub 2024-04-12 13:30:54 +08:00
• 1096717ae9 [Core] Support LoRA on quantized models (#4012) Jee LiandGitHub 2024-04-12 12:02:44 +08:00
• c2b4a1bce9 [Doc] Add typing hints / mypy types cleanup (#3816) 3 people 2024-04-11 17:17:21 -07:00
• e46a60aa4c [BugFix] Fix handling of stop strings and stop token ids (#3672) Nick HillandGitHub 2024-04-11 23:34:12 +01:00
• 1e96c3341a Add extra punica sizes to support bigger vocabs (#4015) Antoni BaumandGitHub 2024-04-11 15:18:57 -07:00
• 95e7d4a97c Fix echo/logprob OpenAI completion bug (#3441) 3 people 2024-04-11 15:15:50 -07:00
• 559eb852f8 [Core] init_distributed_environment align with init_process_group(#4014) youkaichaoandGitHub 2024-04-11 14:00:48 -07:00
• a10d3056da [Core] Set linear_weights directly on the layer (#3977) Antoni BaumandGitHub 2024-04-11 13:35:51 -07:00
• 8afca50889 [Hardware][Intel] Isolate CPUModelRunner and ModelRunner for better maintenance (#3824) bigPYJ1151andGitHub 2024-04-12 02:56:49 +08:00
• 08ccee1e83 punica fix-bgmv-kernel-640 (#4007) fuchen.ljlandGitHub 2024-04-11 23:59:26 +08:00
• c1dc547129 [Kernel] Fused MoE Config for Mixtral 8x22 (#4002) Roger WangandGitHub 2024-04-11 07:50:00 -07:00
• f3d0bf7589 [Doc][Installation] delete python setup.py develop (#3989) youkaichaoandGitHub 2024-04-10 20:33:02 -07:00
• e9da5a40c6 [Misc] Add indirection layer for custom ops (#3913) Kunshang JiandGitHub 2024-04-11 03:26:07 +00:00
• e42df7227d [Test] Add xformer and flash attn tests (#3961) 3 people 2024-04-11 12:09:50 +09:00
• caada5e50a [Core][Model] torch.compile for layernorm in commandr (#3985) youkaichaoandGitHub 2024-04-10 18:48:26 -07:00
• 67b4221a61 [Core][5/N] Fully working chunked prefill e2e (#3884) SangBin ChoandGitHub 2024-04-11 09:56:48 +09:00
• 63e7176f26 [Core][Refactor] move parallel_utils into vllm/distributed (#3950) youkaichaoandGitHub 2024-04-10 15:33:30 -07:00
• 934d3662f7 [Bugfix] handle hf_config with architectures == None (#3982) 3 people 2024-04-10 16:28:25 -06:00
• 92cd2e2f21 [Doc] Fix getting stared to use publicly available model (#3963) FrαnçoisandGitHub 2024-04-10 20:05:52 +02:00
• e4c4072c94 [Bugfix] Remove key sorting for guided_json parameter in OpenAi compatible Server (#3945) Daniel E MarascoandGitHub 2024-04-10 13:15:51 -04:00
• e35397468f [Doc] Add doc to state our model support policy (#3948) 3 people 2024-04-10 10:03:02 -07:00
• 8b317c6dd0 [Model][AMD] ROCm support for 256 head dims for Gemma (#3972) James WhedbeeandGitHub 2024-04-10 10:12:00 -05:00
• bd3c144e0b [Bugfix][ROCm] Add numba to Dockerfile.rocm (#3962) Woosuk KwonandGitHub 2024-04-10 07:37:17 -07:00
• 0258b7a94b [Bugfix] handle prompt_logprobs in _apply_min_tokens_penalty (#3876) Travis JohnsonandGitHub 2024-04-10 02:39:56 -06:00
• b3104b2a10 [Bugfix] Fix logits processor when prompt_logprobs is not None (#3899) 胡译文andGitHub 2024-04-10 15:09:36 +08:00
• c2e00af523 [Bugfix] fix utils.py/merge_dict func TypeError: 'type' object is not subscriptable (#3955) 3 people 2024-04-10 12:49:11 +08:00
• c013d32c75 [Benchmark] Add cpu options to bench scripts (#3915) Zedong PengandGitHub 2024-04-10 12:30:03 +08:00
• 11dd6ebb89 [Misc] Avoid loading incorrect LoRA config (#3777) Jee LiandGitHub 2024-04-10 10:47:15 +08:00
• 6c0b04515f [ROCm][Hardware][AMD] Use Triton Kernel for default FA on ROCm (#3643) 5 people 2024-04-09 17:10:47 -05:00
• e23a43aef8 [Bugfix] Fix KeyError on loading GPT-NeoX (#3925) Junichi SatoandGitHub 2024-04-10 04:11:31 +09:00
• e7c7067b45 [Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837) Cade DanielandGitHub 2024-04-09 11:44:15 -07:00
• 6d592eb430 [Core] separate distributed_init from worker (#3904) youkaichaoandGitHub 2024-04-09 01:49:02 -07:00
• d036198e23 [BugFix][Model] Fix commandr RoPE max_position_embeddings (#3919) RoyandGitHub 2024-04-09 06:17:21 +08:00
• 59a6abf3c9 [Hotfix][CI/Build][Kernel] CUDA 11.8 does not support layernorm optimizations (#3782) Matt WongandGitHub 2024-04-08 14:31:02 -07:00
• bc0c0192d1 [Bugfix] Enable Proper attention_bias Usage in Llama Model Configuration (#3767) 3 people 2024-04-09 01:12:35 +05:30
• f46864d68d [Bugfix] Added Command-R GPTQ support (#3849) 3 people 2024-04-08 17:59:38 +03:00
• b4543c8f6b [Model] add minicpm (#3893) ywfangandGitHub 2024-04-08 18:28:36 +08:00
• 0ce0539d47 [Bugfix] Fix Llava inference with Tensor Parallelism. (#3883) Isotr0pyandGitHub 2024-04-07 22:54:13 +08:00
• 2f19283549 [Core] latency optimization (#3890) youkaichaoandGitHub 2024-04-06 19:14:06 -07:00
• 95baec828f [Core] enable out-of-tree model register (#3871) youkaichaoandGitHub 2024-04-06 17:11:41 -07:00
• e4be7d70bb [CI/Benchmark] add more iteration and use median for robust latency benchmark (#3889) youkaichaoandGitHub 2024-04-06 14:32:30 -07:00
• 54951ac4bf [Bugfix] Fix incorrect output on OLMo models in Tensor Parallelism (#3869) Isotr0pyandGitHub 2024-04-06 03:02:09 +08:00
• 18de883489 [Chunked Prefill][4/n] Chunked prefill scheduler. (#3853) SangBin ChoandGitHub 2024-04-06 02:17:58 +09:00
• 1d7c940d74 Add option to completion API to truncate prompt tokens (#3144) Thomas ParnellandGitHub 2024-04-05 19:15:42 +02:00
• cfaf49a167 [Misc] Define common requirements (#3841) Woosuk KwonandGitHub 2024-04-05 00:39:17 -07:00
• 9edec652e2 [Bugfix] Fixing requirements.txt (#3865) Noam GatandGitHub 2024-04-05 09:46:01 +03:00
• e0dd4d3589 [Misc] Fix linter issues in examples/fp8/quantizer/quantize.py (#3864) Cade DanielandGitHub 2024-04-04 21:57:33 -07:00
• e5043a3e75 [Misc] Add pytest marker to opt-out of global test cleanup (#3863) Cade DanielandGitHub 2024-04-04 21:54:16 -07:00
• d03d64fd2e [CI/Build] refactor dockerfile & fix pip cache youkaichaoandGitHub 2024-04-04 21:53:16 -07:00
• 78107fa091 [Doc]Add asynchronous engine arguments to documentation. (#3810) 4 people 2024-04-04 23:52:01 -05:00
• c391e4b68e [Core] improve robustness of pynccl (#3860) youkaichaoandGitHub 2024-04-04 16:52:12 -07:00
• 9117f892f0 [Model] Cohere CommandR+ (#3829) Saurabh DashandGitHub 2024-04-05 02:01:49 +05:30
• db2a6a41e2 [Hardware][CPU] Update cpu torch to match default of 2.2.1 (#3854) Michael GoinandGitHub 2024-04-04 12:49:49 -07:00
• ca81ff5196 [Core] manage nccl via a pypi package & upgrade to pt 2.2.1 (#3805) youkaichaoandGitHub 2024-04-04 10:26:19 -07:00
• b7782002e1 [Benchmark] Refactor sample_requests in benchmark_throughput (#3613) 3 people 2024-04-04 17:56:22 +08:00
• 819a309c0f [Bugfix] Fix args in benchmark_serving (#3836) 3 people 2024-04-04 00:41:05 -07:00
• aabe8f40f2 [Core] [Frontend] Make detokenization optional (#3749) 3 people 2024-04-03 21:52:18 -07:00
• 498eb5cfa3 [Bugfix] Add kv_scale input parameter to CPU backend (#3840) Woosuk KwonandGitHub 2024-04-03 21:33:08 -07:00
• 537ee25f43 [Core] Enable hf_transfer by default if available (#3817) Michael FeilandGitHub 2024-04-03 21:02:43 -07:00
• 294f8f6665 [BugFix] Pass tokenizer_config to local_tokenizer_group (#3754) Tao HeandGitHub 2024-04-04 11:31:46 +08:00
• b95047f2da [Misc] Publish 3rd meetup slides (#3835) Woosuk KwonandGitHub 2024-04-03 15:46:10 -07:00
• 2ff767b513 Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290) +313 people 2024-04-03 16:15:55 -05:00
• 3dcb3e8b98 [3/N] Refactor scheduler for chunked prefill scheduling (#3550) SangBin ChoandGitHub 2024-04-04 06:13:49 +09:00
• c64cf38673 [Doc] Update contribution guidelines for better onboarding (#3819) Michael FeilandGitHub 2024-04-03 00:31:43 -07:00
• 76b889bf1d [Doc] Update README.md (#3806) Robert ShawandGitHub 2024-04-02 23:11:10 -07:00
• c9b506dad4 [BugFix] Use different mechanism to get vllm version in is_cpu() (#3804) Nick HillandGitHub 2024-04-02 23:06:25 -07:00
• 5757d90e26 [Speculative decoding] Adding configuration object for speculative decoding (#3706) 3 people 2024-04-02 17:40:57 -07:00
• a3c226e7eb [CI/Build] 0.4.0.post1, fix sm 7.0/7.5 binary (#3803) youkaichaoandGitHub 2024-04-02 12:57:04 -07:00
• b321d4881b [Bugfix] Add __init__.py files for vllm/core/block/ and vllm/spec_decode/ (#3798) Michael GoinandGitHub 2024-04-02 12:35:31 -07:00
• ad6eca408b Fix early CUDA init via get_architecture_class_name import (#3770) 3 people 2024-04-03 02:56:26 +08:00
• 205b94942e [CI/Build] fix TORCH_CUDA_ARCH_LIST in wheel build (#3801) youkaichaoandGitHub 2024-04-02 11:54:33 -07:00
• 3bec41f41a [Doc] Fix vLLMEngine Doc Page (#3791) Roger WangandGitHub 2024-04-02 09:49:37 -07:00
• 0739b1947f [Frontend][Bugfix] allow using the default middleware with a root path (#3788) 3 people 2024-04-02 10:20:28 +02:00
• 77a6572aa5 [HotFix] [CI/Build] Minor fix for CPU backend CI (#3787) bigPYJ1151andGitHub 2024-04-02 13:50:53 +08:00
• 0e3f06fe9c [Hardware][Intel] Add CPU inference backend (#3634) 4 people 2024-04-02 13:07:30 +08:00
• eb69d68804 [Misc] [CI/Build] Speed up block manager CPU-only unit tests ~10x by opting-out of GPU cleanup (#3783) Cade DanielandGitHub 2024-04-01 17:49:51 -07:00
• 7d4e1b85e7 [Misc] Add support for new autogptq checkpoint_format (#3689) 3 people 2024-04-02 07:32:01 +08:00
• 93deb0b38f [Speculative decoding 4/9] Lookahead scheduling for speculative decoding (#3250) Cade DanielandGitHub 2024-04-01 15:55:24 -07:00
• ccb58b23e6 [Misc] Fix Benchmark TTFT Calculation for Chat Completions (#3768) Roger WangandGitHub 2024-04-01 15:24:30 -07:00
• 49782fcb76 [Misc] Some minor simplifications to detokenization logic (#3670) Nick HillandGitHub 2024-04-01 13:22:06 -07:00
• f03cc667a0 [Misc] Minor fixes in requirements.txt (#3769) Woosuk KwonandGitHub 2024-04-01 03:15:48 -07:00
• 563c1d7ec5 [CI/Build] Make Marlin Tests Green (#3753) Robert ShawandGitHub 2024-03-30 21:18:34 -05:00
• 9c82a1bec3 [Doc] Update installation doc (#3746) youkaichaoandGitHub 2024-03-30 16:34:38 -07:00
• b6d103542c [Kernel] Layernorm performance optimization (#3662) mawong-amdandGitHub 2024-03-30 14:26:38 -07:00
• 51c31bc10c CMake build elf without PTX (#3739) Simon MoandGitHub 2024-03-29 18:53:08 -07:00
• 3ad438c66f Fix build when nvtools is missing (#3698) bnellnmandGitHub 2024-03-29 21:52:39 -04:00
• 203d4f82ac [Core][Bugfix] cache len of tokenizer (#3741) youkaichaoandGitHub 2024-03-29 18:46:39 -07:00
• 991143cfcd [BugFix] Use consistent logger everywhere (#3738) Nick HillandGitHub 2024-03-29 16:26:44 -07:00
• 8b2d3cbc1b usage lib get version another way (#3735) Simon MoandGitHub 2024-03-29 15:57:08 -07:00
• 9765b5c406 [ROCm][Bugfix] Fixed several bugs related to rccl path and attention selector logic (#3699) Hongxia YangandGitHub 2024-03-29 17:52:36 -04:00
• 430530fc18 bump version to v0.4.0 (#3712) Simon MoandGitHub 2024-03-29 12:28:33 -07:00
• 97356f3c7e [Bugfix] Command-R Max Model Length (#3727) Roger WangandGitHub 2024-03-29 12:27:51 -07:00
• f510395bbf [BugFix][Frontend] Fix completion logprobs=0 error (#3731) RoyandGitHub 2024-03-30 00:38:21 +08:00
• 6110c39dc8 [BugFix] Fix tokenizer out of vocab size (#3685) RoyandGitHub 2024-03-29 23:18:59 +08:00
• d8658c8cc1 Usage Stats Collection (#2852) yhu422andGitHub 2024-03-28 22:16:12 -07:00
• 7bc94a0fdd add ccache to docker build image (#3704) Simon MoandGitHub 2024-03-28 22:14:24 -07:00
• 756b30a5f3 [Core][Test] move local_rank to the last arg with default value(#3711) youkaichaoandGitHub 2024-03-28 21:19:45 -07:00
• 395aa823ea [Misc] Minor type annotation fix (#3716) Woosuk KwonandGitHub 2024-03-28 21:12:24 -07:00
• 26422e477b [Test] Make model tests run again and remove --forked from pytest (#3631) 3 people 2024-03-29 13:06:40 +09:00