nexusquant/pyproject.toml at main · jagmarques/nexusquant · GitHub

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
[build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "nexusquant-kv"
version = "0.5.0"
description = "Training-free KV cache compression (10-33x) via E8 lattice VQ + attention-aware eviction. Asymmetric K/V, real attention scorer, multi-model validated."
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.9"
authors = [{name = "Joao Marques"}]
keywords = [
    "kv-cache", "compression", "quantization", "llm", "inference",
    "e8-lattice", "token-eviction", "transformers", "long-context",
    "memory-efficient", "attention", "vector-quantization",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Science/Research",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Operating System :: OS Independent",
]
dependencies = [
    "torch>=2.0",
    "numpy>=1.24",
    "zstandard>=0.22",
]

[project.optional-dependencies]
hf = ["transformers>=4.40"]
all = ["transformers>=4.40", "accelerate>=0.26"]

[project.urls]
Repository = "https://github.com/jagmarques/nexusquant"

[tool.setuptools.packages.find]
include = ["nexusquant*"]