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 13, 00:45 UTC
main
[Bugfix][NIXL] Fix `block_size_ratio` when logical !=physical blocks (#28925)
Nicolò Lucchesi committed 12 months ago
[Model][Perf] Use cos and sin cache in QwenVL (#28798)
Canlin Guo committed 12 months ago
[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846)
Song Zhixin committed 12 months ago
[BugFix] Fix PP/async scheduling with pooling models (#28899)
Nick Hill committed 12 months ago
[CI/Build] Replace wikipedia url with local server ones (#28908)
Isotr0py committed 12 months ago
[MISC] Remove format.sh (#28906)
Kuntai Du committed 12 months ago
[CI] Fix async scheduling + spec decoding test flake (#28902)
Nick Hill committed 12 months ago
[Misc] Remove unnecessary parentheses from log statements (#28897)
Ning Xie committed 12 months ago
[Doc]: fix typos in various files (#28863)
Didier Durand committed 12 months ago
[Bugfix] Fix wrong CLI defaults for dynamic `SchedulerConfig` fields (#28872)
Cyrus Leung committed 12 months ago
[Refactor] Remove Unused Func in Batch Invariant (#28881)
Wentao Ye committed 12 months ago
[ROCm][Quantization] add apply_vllm_mapper in quark config for models like gpt-oss (#28638)
xuebwang-amd committed 12 months ago
Run macos smoke test workflow on main commit (#28752)
Michael Goin committed 12 months ago
[Bugfix] Fix Kimi-K2 tool parser concatenated tool calls parsing (#28831)
Benjamin Bartels committed 12 months ago
[Misc] Fix wrong comment in scheduler (#28880)
Zhuohan Li committed 12 months ago
[BugFix] Corner case that could cause out-of-sync with external launcher mode and dp >1 (#28774)
Bangsheng Tang committed 12 months ago
[Model] Add Afmoe architecture implementation (#28332)
Pranav committed 12 months ago
[Test] Batch Invariant: Rename and organize tests (#27421)
Wentao Ye committed 12 months ago
[Quantization] [Eagle] Add complete quantization support to the draft model in Eagle (#28435)
Shreyas Kulkarni committed 12 months ago
[BugFix] Fix PP performance and PP kv connector output regression (#28768)
Nick Hill committed 12 months ago