LMCache/pyproject.toml at dev · sdimitro/LMCache · 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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
[build-system]
# Should be mirrored in docker/requirements-build.txt
requires = [
    "ninja",
    "packaging>=24.2",
    "setuptools>=77.0.3,<80.0.0",
    "setuptools_scm>=8",
    "torch==2.6.0",
    "wheel",
]
build-backend = "setuptools.build_meta"

[project]
name = "lmcache"
authors = [{name = "LMCache Team", email = "lmcacheteam@gmail.com"}]
license = "Apache-2.0"
license-files = ["LICENSE"]
readme = "README.md"
description = "A LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios."
classifiers = [
    "Development Status :: 3 - Alpha",
    "Operating System :: POSIX :: Linux",
    "Environment :: GPU",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: Implementation :: CPython",
]
requires-python = ">=3.10,<3.13"
dynamic = ["version"]

[project.scripts]
lmcache_server="lmcache.server.__main__:main"
lmcache_experimental_server="lmcache.experimental.server.__main__:main"
lmcache_controller="lmcache.experimental.api_server.__main__:main"

[project.urls]
homepage = "https://docs.lmcache.ai"
source = "https://github.com/LMCache/LMCache"
issues = "https://github.com/LMCache/LMCache"

[tool.setuptools_scm]
version_file = "lmcache/_version.py"
# do not include +gREV local version, required for Test PyPI upload
local_scheme = "no-local-version"

[tool.setuptools.packages.find]
where = [""]
include = ["lmcache", "lmcache*"]

[tool.ruff]
# Allow lines to be as long as 80.
line-length = 80

[tool.ruff.lint]
select = [
    # pycodestyle
    "E",
    # Pyflakes
    "F",
    # pyupgrade
    # "UP",
    # flake8-bugbear
    "B",
    # isort
    # "I",
]
ignore = [
    # star imports
    "F405", "F403",
    # lambda expression assignment
    "E731",
    # Loop control variable not used within loop body
    "B007",
    # f-string format
    "UP032",
]

[tool.mypy]
python_version = "3.10"

ignore_missing_imports = true
check_untyped_defs = true
follow_imports = "silent"

# After fixing type errors resulting from follow_imports: "skip" -> "silent",
# move the directory here and remove it from format.sh and mypy.yaml
files = [
    "lmcache"
]

# use a custom manylinux image for cibuildwheel that contains CUDA 12.4
[tool.cibuildwheel]
manylinux-x86_64-image = "docker.io/apostab/manylinux-cuda124"
repair-wheel-command = """
auditwheel repair \
  --plat manylinux_2_17_x86_64 \
  --exclude libtorch.so \
  --exclude libtorch_cuda.so \
  --exclude libtorch_python.so \
  --exclude libtorch_cpu.so \
  --exclude libc10.so \
  --exclude libc10_cuda.so \
  -w {dest_dir} {wheel}
"""