vllm/README.md

17 lines
241 B
Markdown
Raw Normal View History

2023-02-09 11:24:15 +00:00
# CacheFlow
2023-02-24 12:04:49 +00:00
## Installation
```bash
pip install psutil numpy torch transformers
pip install flash-attn # This may take up to 10 mins.
2023-02-24 12:04:49 +00:00
pip install -e .
```
## Run
```bash
2023-03-22 04:45:42 +08:00
ray start --head
python server.py [--tensor-parallel-size <N>]
2023-02-24 12:04:49 +00:00
```