@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only
Fork 0

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 1, 22:30 UTC

main

[PD][Nixl] Mamba prefix caching mode support (#42554)

Nicolò Lucchesi committed 5 months ago

[Bugfix] fix EVS for qwen3-vl (#44205)

Rui "Garry" Gao committed 5 months ago

[perf] Add gemma RMS AR fusion (#42646)

Jiahan Chang (Cyrus) committed 5 months ago

Fix Kimi-K2.5 FlashInfer ViT metadata (#44493)

Kevin_Xiong committed 5 months ago

[CI] Reverted gitignore changes (#44497)

Andreas Karatzas committed 5 months ago

← Newer Page 257 of 1120 Older →