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
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45

# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
#
# When uploading crates to the registry Cargo will automatically
# "normalize" Cargo.toml files for maximal compatibility
# with all versions of Cargo and also rewrite `path` dependencies
# to registry (e.g., crates.io) dependencies.
#
# If you are reading this file be aware that the original Cargo.toml
# will likely look very different (and much more reasonable).
# See Cargo.toml.orig for the original contents.

[package]
edition = "2021"
rust-version = "1.63"
name = "kv-cache-size"
version = "0.1.1"
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Exact KV-cache arithmetic for transformer inference: bytes per token, total cache bytes, and the context length that fits a memory budget."
homepage = "https://ml0x.com/"
documentation = "https://ml0x.com/calculators/kv-cache-size-calculator.html"
readme = "README.md"
keywords = [
    "llm",
    "transformer",
    "inference",
    "kv-cache",
    "memory",
]
categories = [
    "mathematics",
    "science",
]
license = "MIT OR Apache-2.0"
repository = "https://github.com/theluckystrike/kv-cache-size"

[lib]
name = "kv_cache_size"
path = "src/lib.rs"

[dependencies]