@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 17, 01:45 UTC

main

[Misc] fix typo in block manager (#4453)

Pastel! committed over 2 years ago

[Misc][Typo] type annotation fix (#4495)

harrywu committed over 2 years ago

[Core] Centralize GPU Worker construction (#4419)

Nick Hill committed over 2 years ago

fix_tokenizer_snapshot_download_bug (#4493)

fuchen.ljl committed over 2 years ago

[Bugfix][Minor] Make ignore_eos effective (#4468)

Li, Jiang committed over 2 years ago

[Core]Refactor gptq_marlin ops (#4466)

Kunshang Ji committed over 2 years ago

[Misc] Upgrade to `torch==2.3.0` (#4454)

Michael Goin committed over 2 years ago

[CI] hotfix: soft fail neuron test (#4458)

Simon Mo committed over 2 years ago

← Newer Page 1059 of 1120 Older →