A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 11:00 UTC
main
[Bugfix][ROCm] Fix AITER MLA V1 (#17880)
vllmellm committed over 1 year ago
[Doc] remove visible token in doc (#17884)
Yan Ma committed over 1 year ago
[Doc] Update several links in reasoning_outputs.md (#17846)
Michael Yao committed over 1 year ago
[Docs] Add Slides from NYC Meetup (#17879)
Simon Mo committed over 1 year ago
[BUGFIX]: return fast when request requires prompt logprobs (#17251)
Ning Xie committed over 1 year ago
[Attention] MLA move rotary embedding to cuda-graph region (#17668)
Lucas Wilkinson committed over 1 year ago
Shanshan Shen committed over 1 year ago
[FEAT][ROCm]: Support AITER MLA on V1 Engine (#17523)
vllmellm committed over 1 year ago
Add cutlass support for blackwell fp8 blockwise gemm (#14383)
Shu Wang committed over 1 year ago
Fix noisy warning for uncalibrated q_scale/p_scale (#17414)
Michael Goin committed over 1 year ago
[CI] Prune down lm-eval small tests (#17012)
Michael Goin committed over 1 year ago
[Test] Attempt all TPU V1 tests, even if some of them fail. (#17334)
yarongmu-google committed over 1 year ago
[V1] Improve VLLM_ALLOW_INSECURE_SERIALIZATION logging (#17860)
Russell Bryant committed over 1 year ago
[CI] Fix test_collective_rpc (#17858)
Russell Bryant committed over 1 year ago
[Misc] Delete LoRA-related redundancy code (#17841)
Jee Jee Li committed over 1 year ago
[Bugfix] `use_fast` failing to be propagated to Qwen2-VL image processor (#17838)
Cyrus Leung committed over 1 year ago
Fix transient dependency error in docs build (#17848)
Harry Mellor committed over 1 year ago
[Misc] add chatbox integration (#17828)
Reid committed over 1 year ago
[Easy] Eliminate c10::optional usage in vllm/csrc (#17819)
Lu Fang committed over 1 year ago
[Doc] Fix a typo in the file name (#17836)
Cyrus Leung committed over 1 year ago