Mooncake/pyproject.toml at main · EmbeddedLLM/Mooncake · 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
108
109
110
111
112
113
114
115
[build-system]
requires = [
    "scikit-build-core>=1.0",
    "pybind11>=2.13",
    "numpy>=1.24",
    # Mooncake PG still builds its Torch ABI extensions through setup.py.
    "setuptools>=61",
    # Multi-ABI PG builds install the requested Torch wheels at build time.
    "pip>=23",
]
build-backend = "scikit_build_core.build"

[project]
name = "mooncake-transfer-engine"
version = "0.3.12.post1"
description = "A KVCache-centric disaggregated architecture for large-scale LLM inference and training."
readme = "README.md"
requires-python = ">=3.10"
license = { file = "LICENSE-APACHE" }
authors = [
    { name = "Mooncake Authors" },
]
dependencies = [
    "aiohttp",
    "msgpack",
    "requests",
]
keywords = ["mooncake", "transfer engine", "kv cache", "llm inference", "rdma"]
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Environment :: GPU :: NVIDIA CUDA",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: Apache Software License",
    "Operating System :: POSIX :: Linux",
    "Programming Language :: C++",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: Implementation :: CPython",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: System :: Distributed Computing",
]

[project.optional-dependencies]
structured = [
    "numpy",
    "pillow",
]
vllm = [
    "fastapi",
    "httpx",
    "msgspec",
    "numpy",
    "pyzmq",
    "torch",
    "vllm",
]
administration = [
    "paramiko",
]
hardware = [
    "torch",
]
dev = [
    "build",
    "cmake-format==0.6.13",
    "codespell==2.2.6",
    "pre-commit==3.7.1",
    "pyright==1.1.411",
    "pytest",
    "ruff==0.6.9",
    "tomli; python_version < '3.11'",
    "twine",
]

[project.urls]
Homepage = "https://github.com/kvcache-ai/Mooncake"
Documentation = "https://kvcache-ai.github.io/Mooncake"
Source = "https://github.com/kvcache-ai/Mooncake"
Issues = "https://github.com/kvcache-ai/Mooncake/issues"
Blog = "https://kvcache.ai/blog"
Changelog = "https://github.com/kvcache-ai/Mooncake/releases"
Slack = "https://join.slack.com/t/mooncake-project/shared_invite/zt-3qx4x35ea-zSSTqTHItHJs9SCoXLOSPA"

[project.scripts]
mooncake_master = "mooncake.cli:main"
mooncake_client = "mooncake.cli_client:main"
transfer_engine_bench = "mooncake.cli_bench:main"
mooncake_http_metadata_server = "mooncake.http_metadata_server:main"
mc_store_rest_server = "mooncake.mooncake_store_service:sync_main"
transfer_engine_topology_dump = "mooncake.transfer_engine_topology_dump:main"

[tool.scikit-build]
minimum-version = "build-system.requires"
build-dir = "build/python/{wheel_tag}"
wheel.packages = ["python/mooncake"]
install.components = ["python"]
sdist.include = [
    "extern/yalantinglibs/**",
    "!extern/yalantinglibs/.git",
]
sdist.exclude = ["extern/yalantinglibs/.git"]

[tool.scikit-build.cmake.define]
BUILD_BENCHMARK = false
BUILD_UNIT_TESTS = false
USE_CUDA = false
WITH_EP = false
WITH_P2P_STORE = false
WITH_STORE_GO = false
WITH_STORE_RUST = false