@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 2, 07:15 UTC

main

fix: glm5.1 pp model loading (#42944)

Uranus committed 5 months ago

docs: fix MLA attention docstring examples (#44118)

nightcityblade committed 5 months ago

[MRV2] Support breakable CUDA graph (#44050)

Woosuk Kwon committed 5 months ago

← Newer Page 264 of 1120 Older →