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 5, 01:00 UTC
main
[Misc] Update `committers.md` (#40058)
Matthew Bonanni committed 7 months ago
[Quantization] Consolidate experts_int8 with fp8 online quantization (#38463)
Asaf Gardin committed 7 months ago
Gate SSU dispatch setup (#40039)
roikoren755 committed 7 months ago
[CI] Add weight transfer tests to CI (#39821)
Sumanth R Hegde committed 7 months ago
[Misc] Add @sfeng33 to CODEOWNERS (#40048)
Flora Feng committed 7 months ago
[Bugfix] Fix bench_serve UTF-8 decode crash on split multi-byte chars (#38732)
Yufeng He committed 7 months ago
[bugfix] Normalize tool message content from array to string format (#39899)
Jared Wen committed 7 months ago
[Bugfix] Fix audioflamingo test (#40052)
Roger Wang committed 7 months ago
[Misc] Move `pyav` and `soundfile` to common requirements (#39997)
Isotr0py committed 7 months ago
Nikita Shapovalov committed 7 months ago
[Refactor] Remove `resampy` dependency (#39524)
Isotr0py committed 7 months ago
[Misc] `toy_proxy_server` handle min_tokens (#39706)
Nicolò Lucchesi committed 7 months ago
[Bugfix] Fix LLM priority normalization for single-string prompts (#40011)
daiyu1111 committed 7 months ago
[Frontend][last/5] Improve pooling entrypoints | clean up. (#39675)
wang.yuqi committed 7 months ago
[Doc] add docs for online quant frontend (#39736)
Vasiliy Kuznetsov committed 7 months ago
[CI/Build] Improve stability of CPU tests (#39966)
Li, Jiang committed 7 months ago
[Model] Use mm_features to compute mrope positions for PaddleOCR-VL (#39888)
grYe99 committed 7 months ago
[Kernel][Helion] Fix inductor fusion of Helion HOP (#39944)
Yanan Cao committed 7 months ago
[Nixl] Bump Nixl version to 0.10.1 (#39922)
Nicolò Lucchesi committed 7 months ago
[Model] Use mm_features for Keye-VL and Keye-1.5-VL M-RoPE (#39869)
lalit10 committed 7 months ago