kv-cache-size 0.1.1

Exact KV-cache arithmetic for transformer inference: bytes per token, total cache bytes, and the context length that fits a memory budget.
Documentation 
1
2
3
4
5
6
7

# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3

[[package]]
name = "kv-cache-size"
version = "0.1.1"