@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

DecodingParams -> SamplingParams

Woosuk Kwon committed over 3 years ago

Add get_len

Woosuk Kwon committed over 3 years ago

Move max_context_len

Woosuk Kwon committed over 3 years ago

Fix slot mapping

Woosuk Kwon committed over 3 years ago

Add Worker class

Woosuk Kwon committed over 3 years ago

Add input metadata

Woosuk Kwon committed over 3 years ago

Minor

Woosuk Kwon committed over 3 years ago

Move worker/models -> models

Woosuk Kwon committed over 3 years ago

Add tests for kernels

Woosuk Kwon committed over 3 years ago

Add reshape_and_cache op

Woosuk Kwon committed over 3 years ago

cache_kernel -> cache_kernels

Woosuk Kwon committed over 3 years ago

Remove redundant fn

Woosuk Kwon committed almost 4 years ago

Add gitignore

Woosuk Kwon committed almost 4 years ago

Implement cache ops

Woosuk Kwon committed almost 4 years ago

Minor

Woosuk Kwon committed almost 4 years ago

Fix return type error

Woosuk Kwon committed almost 4 years ago

Add warning

Woosuk Kwon committed almost 4 years ago

Fix KVCache shape

Woosuk Kwon committed almost 4 years ago

Add __repr__

Woosuk Kwon committed almost 4 years ago

Fix a ref count bug in swapping

Woosuk Kwon committed almost 4 years ago

← Newer Page 1118 of 1120 Older →