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, 08:30 UTC
main
[Bugfix] Fix cpu usage and cache hit stats reporting on cpu environment (#18674)
Yuqi Zhang committed over 1 year ago
[doc] improve readability (#18675)
Reid committed over 1 year ago
[doc] fix broken links (#18671)
Reid committed over 1 year ago
[Misc] Reduce logs on startup (#18649)
Cyrus Leung committed over 1 year ago
[BUGFIX] catch subclass first for try...except (#18672)
Ning Xie committed over 1 year ago
Speed up the `kernels/quantization/` tests (#18669)
Michael Goin committed over 1 year ago
[VLM] Initialize video input support for InternVL models (#18499)
Isotr0py committed over 1 year ago
[Misc][ModelScope] Change to use runtime VLLM_USE_MODELSCOPE (#18655)
Mengqing Cao committed over 1 year ago
[Misc]Replace `cuda` hard code with `current_platform` in Ray (#14668)
Chenguang Li committed over 1 year ago
[MISC] correct signature for LoaderFunction (#18670)
Ning Xie committed over 1 year ago
Seiji Eicher committed over 1 year ago
[BugFix][Spec Decode] Improve Prefix Caching Logic in Speculative Decoding (#18668)
Woosuk Kwon committed over 1 year ago
[CI/Build] fix permission denied issue (#18645)
Reid committed over 1 year ago
fix(regression): clone from reference items (#18662)
Aaron Pham committed over 1 year ago
[CI] enforce import regex instead of re (#18665)
Aaron Pham committed over 1 year ago
[BugFix] Fix import error for fused_moe (#18642)
wangxiyuan committed over 1 year ago
[MISC] typo fix and clean import (#18664)
Ning Xie committed over 1 year ago
[CI/Build] `chmod +x` to `cleanup_pr_body.sh` (#18650)
Cyrus Leung committed over 1 year ago
[Doc] Reorganize user guide (#18661)
Cyrus Leung committed over 1 year ago
[Model] use AutoWeightsLoader for gpt2 (#18625)
ztang2370 committed over 1 year ago