Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 55712941e5 [Bug Fix] Illegal memory access, FP8 Llama 3.1 405b (#6852) Lucas WilkinsonandGitHub 2024-07-26 22:27:44 -04:00
• 981b0d5673 [Frontend] Factor out code for running uvicorn (#6828) Cyrus LeungandGitHub 2024-07-27 09:58:25 +08:00
• d09b94ca58 [TPU] Support collective communications in XLA devices (#6813) Woosuk KwonandGitHub 2024-07-26 18:45:57 -07:00
• bb5494676f enforce eager mode with bnb quantization temporarily (#6846) chenqianfzhandGitHub 2024-07-26 18:32:20 -07:00
• b5f49ee55b Update README.md (#6847) Gurpreet Singh DhamiandGitHub 2024-07-26 20:26:45 -04:00
• 150a1ffbfd [Doc] Update SkyPilot doc for wrong indents and instructions for update service (#4283) Zhanghao WuandGitHub 2024-07-26 17:39:10 -04:00
• 281977bd6e [Doc] Add Nemotron to supported model docs (#6843) Michael GoinandGitHub 2024-07-26 17:32:44 -04:00
• 3bbb4936dc [Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend and update documentation (#6125) Li, JiangandGitHub 2024-07-27 04:50:10 +08:00
• aa4867791e [Misc][TPU] Support TPU in initialize_ray_cluster (#6812) Woosuk KwonandGitHub 2024-07-26 12:39:49 -07:00
• 71734f1bf2 [Build/CI][ROCm] Minor simplification to Dockerfile.rocm (#6811) Woosuk KwonandGitHub 2024-07-26 12:28:32 -07:00
• 50704f52c4 [Bugfix][Kernel] Promote another index to int64_t (#6838) Tyler Michael SmithandGitHub 2024-07-26 14:41:04 -04:00
• 07278c37dd [Model] Support Nemotron models (Nemotron-3, Nemotron-4, Minitron) (#6611) Michael GoinandGitHub 2024-07-26 14:33:42 -04:00
• 85ad7e2d01 [doc][debugging] add known issues for hangs (#6816) youkaichaoandGitHub 2024-07-25 21:48:05 -07:00
• 89a84b0bb7 [Core] Use array to speedup padding (#6779) Peng GuanwenandGitHub 2024-07-26 12:31:31 +08:00
• 084a01fd35 [Bugfix] [Easy] Fixed a bug in the multiprocessing GPU executor. (#6770) Anthony PlataniosandGitHub 2024-07-26 00:25:35 -04:00
• 062a1d0fab Fix ReplicatedLinear weight loading (#6793) QQSongandGitHub 2024-07-25 19:24:58 -07:00
• 2eb9f4ff26 [ci] Mark tensorizer as soft fail and separate from grouped test (#6810) Kevin H. LuuandGitHub 2024-07-25 18:08:33 -07:00
• 443c7cf4cf [ci][distributed] fix flaky tests (#6806) youkaichaoandGitHub 2024-07-25 17:44:09 -07:00
• 1adddb14bf [Core] Fix ray forward_dag error mssg (#6792) SangBin ChoandGitHub 2024-07-25 16:53:25 -07:00
• b7215de2c5 [Docs] Publish 5th meetup slides (#6799) Woosuk KwonandGitHub 2024-07-25 16:47:55 -07:00
• f3ff63c3f4 [doc][distributed] improve multinode serving doc (#6804) youkaichaoandGitHub 2024-07-25 15:38:32 -07:00
• cd7edc4e87 [Bugfix] Fix empty (nullptr) channelwise scales when loading wNa16 using compressed tensors (#6798) Lucas WilkinsonandGitHub 2024-07-25 18:05:09 -04:00
• 6a1e25b151 [Doc] Add documentations for nightly benchmarks (#6412) Kuntai DuandGitHub 2024-07-25 11:57:16 -07:00
• 95db75de64 [Bugfix] Add synchronize to prevent possible data race (#6788) 3 people 2024-07-25 13:40:01 -04:00
• 65b1f121c8 [Bugfix] Fix kv_cache_dtype=fp8 without scales for FP8 checkpoints (#6761) Michael GoinandGitHub 2024-07-25 12:46:15 -04:00
• 889da130e7 [ Misc ] fp8-marlin channelwise via compressed-tensors (#6524) 3 people 2024-07-25 09:46:04 -07:00
• b75e314fff [Bugfix] Add image placeholder for OpenAI Compatible Server of MiniCPM-V (#6787) 4 people 2024-07-26 00:42:49 +08:00
• 316a41ac1d [Bugfix] Fix encoding_format in examples/openai_embedding_client.py (#6755) Chang SuandGitHub 2024-07-24 22:48:07 -07:00
• 0310029a2f [Bugfix] Fix awq_marlin and gptq_marlin flags (#6745) Alexander MatveevandGitHub 2024-07-25 01:34:11 -04:00
• 309aaef825 [Bugfix] Fix decode tokens w. CUDA graph (#6757) Cody YuandGitHub 2024-07-24 22:33:56 -07:00
• 9e169a4c61 [Model] Adding support for MiniCPM-V (#4087) AlphiandGitHub 2024-07-25 11:59:30 +08:00
• 5689e256ba [Frontend] Represent tokens with identifiable strings (#6626) Evan Z. LiuandGitHub 2024-07-24 18:51:00 -07:00
• 740374d456 [core][distributed] fix zmq hang (#6759) youkaichaoandGitHub 2024-07-24 17:37:12 -07:00
• d88c458f44 [Doc][AMD][ROCm]Added tips to refer to mi300x tuning guide for mi300x users (#6754) Hongxia YangandGitHub 2024-07-24 17:32:57 -04:00
• 421e218b37 [Bugfix] Bump transformers to 4.43.2 (#6752) Michael GoinandGitHub 2024-07-24 16:22:16 -04:00
• 5448f67635 [Core] Tweaks to model runner/input builder developer APIs (#6712) Antoni BaumandGitHub 2024-07-24 12:17:12 -07:00
• 0e63494cf3 Add fp8 support to reshape_and_cache_flash (#6667) Antoni BaumandGitHub 2024-07-24 11:36:52 -07:00
• ee812580f7 [Frontend] split run_server into build_server and run_server (#6740) DanieleandGitHub 2024-07-24 19:36:04 +02:00
• 40468b13fa [Bugfix] Miscalculated latency lead to time_to_first_token_seconds inaccurate. (#6686) Allen.DouandGitHub 2024-07-24 23:58:42 +08:00
• 2cf0df3381 [Bugfix] Fix speculative decode seeded test (#6743) Nick HillandGitHub 2024-07-24 08:58:31 -07:00
• 545146349c Adding f-string to validation error which is missing (#6748) LF MarquesandGitHub 2024-07-24 16:55:53 +01:00
• f4f8a9d892 [Bugfix]fix modelscope compatible issue (#6730) liuyhwangyhandGitHub 2024-07-24 20:04:46 +08:00
• b570811706 [Build/CI] Update run-amd-test.sh. Enable Docker Hub login. (#6711) Alexei-V-Ivanov-AMDandGitHub 2024-07-24 07:01:14 -05:00
• ccc4a73257 [Docs][ROCm] Detailed instructions to build from source (#6680) Woosuk KwonandGitHub 2024-07-24 01:07:23 -07:00
• 0a740a11ba [Bugfix] Fix token padding for chameleon (#6724) Roger WangandGitHub 2024-07-24 01:05:09 -07:00
• c882a7f5b3 [SpecDecoding] Update MLPSpeculator CI tests to use smaller model (#6714) Nick HillandGitHub 2024-07-24 00:34:22 -07:00
• 5e8ca973eb [Bugfix] fix flashinfer cudagraph capture for PP (#6708) William LinandGitHub 2024-07-23 18:49:44 -07:00
• 87525fab92 [bitsandbytes]: support read bnb pre-quantized model (#5753) 3 people 2024-07-23 16:45:09 -07:00
• 2f808e69ab [Bugfix] StatLoggers: cache spec decode metrics when they get collected. (#6645) Thomas ParnellandGitHub 2024-07-24 01:05:05 +02:00
• 01c16ede6b [CI] Add smoke test for non-uniform AutoFP8 quantization (#6702) Michael GoinandGitHub 2024-07-23 18:45:12 -04:00
• 72fc704803 [build] relax wheel size limit (#6704) youkaichaoandGitHub 2024-07-23 14:03:49 -07:00
• 1bedf210e3 Bump transformers version for Llama 3.1 hotfix and patch Chameleon (#6690) Roger WangandGitHub 2024-07-23 13:47:48 -07:00
• 507ef787d8 [Model] Pipeline Parallel Support for DeepSeek v2 (#6519) Travis JohnsonandGitHub 2024-07-23 13:22:09 -06:00
• 58f53034ad [Frontend] Add Usage data in each chunk for chat_serving. #6540 (#6652) Yehoshua CohenandGitHub 2024-07-23 21:41:55 +03:00
• 0eb0757bef [Misc] Add ignored layers for fp8 quantization (#6657) Michael GoinandGitHub 2024-07-23 14:04:04 -04:00
• 38c4b7e863 Bump version to 0.5.3.post1 (#6696) Simon MoandGitHub 2024-07-23 10:08:59 -07:00
• a112a84aad [BugFix] Fix RoPE error in Llama 3.1 (#6693) Woosuk KwonandGitHub 2024-07-23 09:46:05 -07:00
• 461089a21a [Bugfix] Fix a log error in chunked prefill (#6694) Woosuk KwonandGitHub 2024-07-23 09:27:58 -07:00
• 71950af726 [doc][distributed] fix doc argument order (#6691) youkaichaoandGitHub 2024-07-23 08:55:33 -07:00
• cb1362a889 [Docs] Announce llama3.1 support (#6688) Woosuk KwonandGitHub 2024-07-23 08:18:15 -07:00
• bb2fc08072 Bump version to v0.5.3 (#6674) Simon MoandGitHub 2024-07-23 00:00:08 -07:00
• 3eda4ec780 support ignore patterns in model loader (#6673) Simon MoandGitHub 2024-07-22 23:59:42 -07:00
• 22fa2e35cb [VLM][Model] Support image input for Chameleon (#6633) Roger WangandGitHub 2024-07-22 23:50:48 -07:00
• c5201240a4 [misc] only tqdm for first rank (#6672) youkaichaoandGitHub 2024-07-22 21:57:27 -07:00
• 97234be0ec [Misc] Manage HTTP connections in one place (#6600) Cyrus LeungandGitHub 2024-07-23 12:32:02 +08:00
• c051bfe4eb [doc][distributed] doc for setting up multi-node environment (#6529) youkaichaoandGitHub 2024-07-22 21:22:09 -07:00
• 9e0b558a09 [Misc] Support FP8 kv cache scales from compressed-tensors (#6528) Michael GoinandGitHub 2024-07-23 00:11:50 -04:00
• e519ae097a add tqdm when loading checkpoint shards (#6569) 4 people 2024-07-23 11:48:01 +08:00
• 7c2749a4fd [misc] add start loading models for users information (#6670) youkaichaoandGitHub 2024-07-22 20:08:02 -07:00
• 729171ae58 [Misc] Enable chunked prefill by default for long context models (#6666) Woosuk KwonandGitHub 2024-07-22 20:03:13 -07:00
• c5e8330997 [Bugfix] Fix null modules_to_not_convert in FBGEMM Fp8 quantization (#6665) Cheng LiandGitHub 2024-07-22 19:25:05 -07:00
• e0c15758b8 [Core] Modulize prepare input and attention metadata builder (#6596) Cody YuandGitHub 2024-07-22 17:45:24 -07:00
• bdf5fd1386 [Misc] Remove deprecation warning for beam search (#6659) Woosuk KwonandGitHub 2024-07-22 17:21:58 -07:00
• 5a96ee52a3 [ci][build] add back vim in docker (#6661) youkaichaoandGitHub 2024-07-22 16:26:29 -07:00
• 42c7f66a38 [Core] Support dynamically loading Lora adapter from HuggingFace (#6234) 3 people 2024-07-22 15:42:40 -07:00
• 69d5ae38dc [ci] Use different sccache bucket for CUDA 11.8 wheel build (#6656) Kevin H. LuuandGitHub 2024-07-22 14:20:41 -07:00
• fea59c7712 [Bugfix][Kernel] Use int64_t for indices in fp8 quant kernels (#6649) Tyler Michael SmithandGitHub 2024-07-22 16:08:30 -04:00
• 739b61a348 [Frontend] Refactor prompt processing (#4028) 3 people 2024-07-23 01:13:53 +08:00
• 89c1c6a196 [Bugfix] Fix vocab_size field access in llava_next.py (#6624) Jae-Won ChungandGitHub 2024-07-22 01:02:51 -04:00
• 42de2cefcb [Misc] Add a wrapper for torch.inference_mode (#6618) Woosuk KwonandGitHub 2024-07-21 18:43:11 -07:00
• c9eef37f32 [Model] Initial Support for Chameleon (#5770) Roger WangandGitHub 2024-07-21 17:37:51 -07:00
• 396d92d5e0 [Kernel][Core] Add AWQ support to the Marlin kernel (#6612) Alexander MatveevandGitHub 2024-07-21 19:41:42 -04:00
• 25e778aa16 [Model] Refactor and decouple phi3v image embedding (#6621) Isotr0pyandGitHub 2024-07-22 07:07:58 +08:00
• b6df37f943 [Misc] Remove abused noqa (#6619) Woosuk KwonandGitHub 2024-07-21 08:47:04 -07:00
• 14f91fe67c [Spec Decode] Disable Log Prob serialization to CPU for spec decoding for both draft and target models. (#6485) sroy745andGitHub 2024-07-20 23:58:58 -07:00
• d7f4178dd9 [Frontend] Move chat utils (#6602) 3 people 2024-07-21 08:38:17 +08:00
• 082ecd80d5 [ Bugfix ] Fix AutoFP8 fp8 marlin (#6609) Robert ShawandGitHub 2024-07-20 19:25:56 -04:00
• f952bbc8ff [Misc] Fix input_scale typing in w8a8_utils.py (#6579) Michael GoinandGitHub 2024-07-20 19:11:13 -04:00
• 9364f74eee [ Kernel ] Enable fp8-marlin for fbgemm-fp8 models (#6606) Robert ShawandGitHub 2024-07-20 14:50:10 -04:00
• 06d6c5fe9f [Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes (#6543) Matt WongandGitHub 2024-07-20 11:39:07 -05:00
• 683e3cb9c4 [ Misc ] fbgemm checkpoints (#6559) Robert ShawandGitHub 2024-07-20 12:36:57 -04:00
• 9042d68362 [Misc] Consolidate and optimize logic for building padded tensors (#6541) Cyrus LeungandGitHub 2024-07-20 12:17:24 +08:00
• 3f8d42c81f Pipeline Parallel: Guard for KeyErrors at request abort (#6587) Travis JohnsonandGitHub 2024-07-19 20:18:19 -06:00
• 7bd82002ae [Core] Allow specifying custom Executor (#6557) Antoni BaumandGitHub 2024-07-19 18:25:06 -07:00
• 2e26564259 [ Kernel ] FP8 Dynamic Per Token Quant - Add scale_ub (#6593) 3 people 2024-07-19 21:15:26 -04:00
• e81522e879 [build] add ib in image for out-of-the-box infiniband support (#6599) youkaichaoandGitHub 2024-07-19 17:16:57 -07:00
• 45ceb85a0c [Docs] Update PP docs (#6598) Murali AndoorveeduandGitHub 2024-07-19 19:38:21 -04:00
• 4cc24f01b1 [ Kernel ] Enable Dynamic Per Token fp8 (#6547) Robert ShawandGitHub 2024-07-19 19:08:15 -04:00
• 07eb6f19f3 [bugfix][distributed] fix multi-node bug for shared memory (#6597) youkaichaoandGitHub 2024-07-19 15:34:34 -07:00
• f0bbfaf917 [Bugfix] [SpecDecode] AsyncMetricsCollector: update time since last collection (#6578) Thomas ParnellandGitHub 2024-07-19 23:01:03 +02:00