turboquant/pyproject.toml at main · back2matching/turboquant · 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
46
47
[build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "turboquant"
version = "0.3.1"
description = "LLM runs 2x faster at long context. Compresses KV cache to 4 bits — drop-in for any HuggingFace model."
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.10"
authors = [
    {name = "back2matching"},
]
keywords = ["llm", "kv-cache", "quantization", "inference", "turboquant", "transformers"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
    "torch>=2.2.0",
    "transformers>=4.40.0",
    "scipy>=1.10.0",
    "numpy>=1.24.0",
]

[project.optional-dependencies]
server = ["uvicorn", "fastapi"]
dev = ["pytest", "pytest-benchmark"]

[project.urls]
Homepage = "https://github.com/back2matching/turboquant"
Issues = "https://github.com/back2matching/turboquant/issues"

[project.scripts]
turboquant-server = "turboquant.server:main"
turboquant-eval = "turboquant.eval:main"

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