vllm-i64/pyproject.toml at main · Complexity-ML/vllm-i64 · 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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
[build-system]
requires = ["setuptools>=68.0", "wheel", "torch>=2.0"]
build-backend = "setuptools.build_meta"

[project]
name = "vllm-i64"
version = "0.3.0"
description = "Integer-first inference engine for token-routed language models"
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.10"
authors = [
    {name = "INL / Complexity-ML"},
]
keywords = ["inference", "llm", "token-routing", "i64", "moe"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "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>=2.0",
    "numpy>=1.24",
    "aiohttp>=3.9",
    "tokenizers>=0.15",
    "prometheus-client>=0.17",
    "safetensors>=0.4",
    "transformers>=4.38",
    "huggingface-hub>=0.20",
]

[project.optional-dependencies]
dev = [
    "pytest>=7.0",
    "pytest-asyncio>=0.21",
    "httpx>=0.24",
]
cuda = [
    "ninja>=1.11",
]
flash = [
    "flash-attn>=2.5",
]
lora = [
    "safetensors>=0.4",
]

[project.scripts]
vllm-i64 = "vllm_i64.cli:main"

[project.urls]
Homepage = "https://github.com/Complexity-ML/vllm-i64"
Repository = "https://github.com/Complexity-ML/vllm-i64"

[tool.setuptools.packages.find]
include = ["vllm_i64*"]

[tool.pytest.ini_options]
testpaths = ["tests"]