@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 expert_ids shape in MoE (#4517)

Woosuk Kwon committed over 2 years ago

[Misc] Remove Mixtral device="cuda" declarations (#4543)

Philipp Moritz committed over 2 years ago

[Core][Distributed] fix pynccl del error (#4508)

youkaichao committed over 2 years ago

[Bugfix] Add validation for seed (#4529)

sasha0552 committed over 2 years ago

[Kernel] Update fused_moe tuning script for FP8 (#4457)

Philipp Moritz committed over 2 years ago

[Bugfix] Use random seed if seed is -1 (#4531)

sasha0552 committed over 2 years ago

[Bugfix] Fix 307 Redirect for `/metrics` (#4523)

Robert Shaw committed over 2 years ago

[Test] Add ignore_eos test (#4519)

SangBin Cho committed over 2 years ago

← Newer Page 1058 of 1120 Older →