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, 17:15 UTC
main
[Bugfix][Frontend] Eliminate regex based check in reasoning full generator (#14821)
Ce Gao committed over 1 year ago
[Misc] Fix test_sleep to use query parameters (#14373)
Lize Cai committed over 1 year ago
[Bugfix] Fix 'InductorAdaptor object has no attribute 'cache_dir' (#15674)
Jee Jee Li committed over 1 year ago
[CPU][CI] Improve CPU Dockerfile (#15690)
Li, Jiang committed over 1 year ago
[Refactor][Frontend] Keep all logic about reasoning into one class (#14428)
Ce Gao committed over 1 year ago
[TPU][CI] Fix TPUModelRunner Test (#15667)
Robert Shaw committed over 1 year ago
[V1] Remove legacy input registry (#15673)
Cyrus Leung committed over 1 year ago
[Bugfix] Fix `mm_hashes` forgetting to be passed (#15668)
Cyrus Leung committed over 1 year ago
Refactor error handling for multiple exceptions in preprocessing (#15650)
Jason (Siyu) Zhu committed over 1 year ago
[Quantization][FP8] Adding support for fp8 gemm layer input in fp8 (#14578)
Gregory Shtrasberg committed over 1 year ago
[Misc]add coding benchmark for speculative decoding (#15303)
Chen Xia committed over 1 year ago
Revert "Use Cache Hinting for fused_moe kernel (#15511)" (#15645)
Wes committed over 1 year ago
[CI][TPU] Temporarily Disable Quant Test on TPU (#15649)
Robert Shaw committed over 1 year ago
[Doc] Fix dead links in Job Board (#15637)
wwl2755 committed over 1 year ago
[Bugfix] Fix failure to launch in Tensor Parallel TP mode on macOS. (#14948)
Kebe committed over 1 year ago
[Quantization][V1] BitsAndBytes support V1 (#15611)
Jee Jee Li committed over 1 year ago
Robert Shaw committed over 1 year ago
[V1] AsyncLLM data parallel (#13923)
Nick Hill committed over 1 year ago
[CI] Update rules for applying `tpu` label. (#15634)
Russell Bryant committed over 1 year ago
Correct PowerPC to modern IBM Power (#15635)
cnorman committed over 1 year ago