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
[CI/Build] Remove imports of built-in `re` (#18750)
Cyrus Leung committed over 1 year ago
Hyogeun Oh (오효근) committed over 1 year ago
Shawn Huang committed over 1 year ago
[Build] fix cpu build missing libtbbmalloc.so (#18744)
Kebe committed over 1 year ago
Minor fix about MooncakeStoreConnector (#18721)
maobaolong committed over 1 year ago
[Doc] cleanup deprecated flag for doc (#18715)
Calvin Chen committed over 1 year ago
Łukasz Durejko committed over 1 year ago
feat(rocm-support): support mamba2 on rocm (#18565)
almersawi committed over 1 year ago
Reid committed over 1 year ago
[Doc] Update reproducibility doc and example (#18741)
Cyrus Leung committed over 1 year ago
[Doc] Update OOT model docs (#18742)
Cyrus Leung committed over 1 year ago
[FEAT] [ROCm] Upgrade AITER Fused MoE kernels. (#18271)
vllmellm committed over 1 year ago
[Model][Gemma3] Cast image pixel values already on CPU (#18732)
Lukas Geiger committed over 1 year ago
[V1][Quantization] Add CUDA graph compatible v1 GGUF support (#18646)
Isotr0py committed over 1 year ago
[Misc] improve web section group title display (#18684)
Reid committed over 1 year ago
[Model][Gemma3] Simplify image input validation (#18710)
Lukas Geiger committed over 1 year ago
Convert `examples` to `ruff-format` (#18400)
Harry Mellor committed over 1 year ago
Lukas Geiger committed over 1 year ago
[Bugfix] Fix Llama GGUF initialization (#18717)
Cyrus Leung committed over 1 year ago
[Doc] Move examples and further reorganize user guide (#18666)
Cyrus Leung committed over 1 year ago