@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, 09:15 UTC

main

Fix double free

Woosuk Kwon committed almost 4 years ago

Minor

Woosuk Kwon committed almost 4 years ago

Minor

Woosuk Kwon committed almost 4 years ago

Fix memory leak in swapping

Woosuk Kwon committed almost 4 years ago

Fix bugs in scheduler

Woosuk Kwon committed almost 4 years ago

Fix a bug in swap_in and swap_out

Woosuk Kwon committed almost 4 years ago

Fix can_swap_in

Woosuk Kwon committed almost 4 years ago

Fix typo

Woosuk Kwon committed almost 4 years ago

Fix typo

Woosuk Kwon committed almost 4 years ago

Fix get_model

Woosuk Kwon committed almost 4 years ago

Fix typo

Woosuk Kwon committed almost 4 years ago

Fix scheduler

Woosuk Kwon committed almost 4 years ago

Add model_utils

Woosuk Kwon committed almost 4 years ago

Fix cache engine

Woosuk Kwon committed almost 4 years ago

Add scheduler

Woosuk Kwon committed almost 4 years ago

Add find method to sequence group

Woosuk Kwon committed almost 4 years ago

Fix can_swap_in

Woosuk Kwon committed almost 4 years ago

SERVING -> RUNNING

Woosuk Kwon committed almost 4 years ago

BlockAllocator -> BlockManager

Woosuk Kwon committed almost 4 years ago

Add blank setup file

Woosuk Kwon committed almost 4 years ago

← Newer Page 1119 of 1120 Older →