Add memory analyzer & utomatically configure KV cache size (#6)

This commit is contained in:
Woosuk Kwon
2023-03-11 23:23:14 -08:00
committed by GitHub
parent 1a7eb7da61
commit e9d3f2ff77
7 changed files with 216 additions and 34 deletions

View File

@@ -3,7 +3,7 @@
## Installation
```bash
pip install cmake torch transformers
pip install psutil numpy torch transformers
pip install flash-attn # This may take up to 10 mins.
pip install -e .
```