Woosuk Kwon d359cda5fa Minor
2023-03-26 08:00:39 +00:00
2023-03-26 08:00:39 +00:00
2023-03-13 13:48:38 -07:00
2023-02-16 07:47:21 +00:00
2023-03-21 13:45:42 -07:00
2023-03-21 13:45:42 -07:00

CacheFlow

Installation

pip install psutil numpy torch transformers
pip install flash-attn # This may take up to 10 mins.
pip install -e .

Run

ray start --head
python server.py [--tensor-parallel-size <N>]
S
Description
A high-throughput and memory-efficient inference and serving engine for LLMs
Readme Apache-2.0 40 MiB
Languages
Python 85%
Cuda 10.2%
C++ 3.1%
C 0.6%
Shell 0.6%
Other 0.4%