forked from vllm-project/vllm-omni
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpyproject.toml
More file actions
220 lines (201 loc) · 6.38 KB
/
pyproject.toml
File metadata and controls
220 lines (201 loc) · 6.38 KB
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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
[build-system]
requires = [
"setuptools>=77.0.3,<81.0.0",
"wheel",
"setuptools-scm>=8.0",
]
build-backend = "setuptools.build_meta"
[project]
name = "vllm-omni"
dynamic = ["version", "dependencies"]
description = "A framework for efficient model inference with omni-modality models"
readme = "README.md"
requires-python = ">=3.10,<3.14"
license = "Apache-2.0"
authors = [
{name = "vLLM-Omni Team"}
]
keywords = ["vllm", "multimodal", "diffusion", "transformer", "inference", "serving"]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Libraries :: Python Modules",
]
# Dependencies are now managed dynamically via setup.py based on detected hardware platform.
# This allows automatic installation of the correct platform-specific dependencies (CUDA/ROCm/CPU/XPU/NPU)
# without requiring extras like [cuda]. See requirements/ directory for platform-specific dependencies.
# Note: vllm is intentionally excluded due to entrypoints overwrite issue.
[project.optional-dependencies]
dev = [
"pytest>=7.0.0",
"pytest-asyncio>=0.21.0",
"pytest-cov>=4.0.0",
"pytest-mock>=3.10.0",
"datasets>=2.14.0",
"mypy==1.11.1",
"pre-commit==4.0.1",
"openai-whisper>=20250625",
"psutil>=7.2.0",
"soundfile>=0.13.1",
"imageio[ffmpeg]>=0.6.0",
"opencv-python>=4.12.0.88",
"mooncake-transfer-engine==0.3.8.post1",
"av", # for ComfyUI tests
"openpyxl>=3.0.0", # for nightly CI
"pyttsx3>=2.99",
"mistune>=3.2.0", # for example tests
]
demo = [
"gradio>=6.7.0",
]
docs = [
"mkdocs>=1.5.0",
"mkdocs-api-autonav",
"mkdocs-material",
"mkdocstrings-python",
"mkdocs-gen-files",
"mkdocs-awesome-nav",
"mkdocs-glightbox",
"mkdocs-git-revision-date-localized-plugin",
"mkdocs-minify-plugin",
"regex",
"ruff",
"pydantic",
]
[project.urls]
Homepage = "https://github.com/vllm-project/vllm-omni"
Repository = "https://github.com/vllm-project/vllm-omni"
Documentation = "https://vllm-omni.readthedocs.io"
"Bug Tracker" = "https://github.com/vllm-project/vllm-omni/issues"
[project.scripts]
vllm = "vllm_omni.entrypoints.cli.main:main"
vllm-omni = "vllm_omni.entrypoints.cli.main:main"
[tool.setuptools.packages.find]
where = ["."]
include = ["vllm_omni*"]
[tool.setuptools.package-data]
"vllm_omni" = ["_version.py", "py.typed"]
"vllm_omni.model_executor.stage_configs" = ["*.yaml"]
[tool.setuptools_scm]
# no extra settings needed, presence enables setuptools-scm
[tool.ruff]
line-length = 120
exclude = [
".eggs",
".git",
".hg",
".mypy_cache",
".tox",
".venv",
"build",
"dist",
"vllm_omni.egg-info",
]
[tool.ruff.lint]
select = [
"E", # pycodestyle errors
"W", # pycodestyle warnings
"F", # pyflakes
"I", # isort (handled separately, but included for compatibility)
"N", # pep8-naming
"UP", # pyupgrade
]
ignore = [
"E203", # whitespace before ':' (conflicts with black)
# W503 is not needed in ruff as it's compatible with black by default
"N801", # class names should use CapWords convention
"N802", # function name should follow snake_case
"N806", # variable in function should follow snake_case
"N812", # lowercase imported as non-lowercase: functional as F
]
[tool.ruff.lint.per-file-ignores]
"examples/**" = ["E501"] # Allow long lines in examples
"tests/**" = ["E501"] # Allow long lines in tests
[tool.mypy]
python_version = "3.12, 3.13"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
[tool.pytest.ini_options]
asyncio_mode = "auto"
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
addopts = [
"--strict-markers",
"--strict-config"
]
markers = [
# ci/cd required
"core_model: L1&L2 tests (run in each PR)",
"advanced_model: L3&L4 level tests (run in each merge or nightly)",
# function module markers
"diffusion: Diffusion model tests",
"omni: Omni model tests",
"cache: Cache backend tests",
"parallel: Parallelism/distributed tests",
"example: Doc example code tests",
# platform markers
"cpu: Tests that run on CPU",
"gpu: Tests that run on GPU (auto-added)",
"cuda: Tests that run on CUDA (auto-added)",
"rocm: Tests that run on AMD/ROCm (auto-added)",
"xpu: Tests that run on XPU (auto-added)",
"npu: Tests that run on NPU/Ascend (auto-added)",
# specified computation resources marks (auto-added)
"H100: Tests that require H100 GPU",
"L4: Tests that require L4 GPU",
"MI325: Tests that require MI325 GPU (AMD/ROCm)",
"A2: Tests that require A2 NPU",
"A3: Tests that require A3 NPU",
"distributed_cuda: Tests that require multi cards on CUDA platform",
"distributed_rocm: Tests that require multi cards on ROCm platform",
"distributed_xpu: Tests that require multi cards on XPU platform",
"distributed_npu: Tests that require multi cards on NPU platform",
"skipif_cuda: Skip if the num of CUDA cards is less than the required",
"skipif_rocm: Skip if the num of ROCm cards is less than the required",
"skipif_xpu: Skip if the num of XPU cards is less than the required",
"skipif_npu: Skip if the num of NPU cards is less than the required",
# more detailed markers
"slow: Slow tests (may skip in quick CI)",
"benchmark: Benchmark tests",
]
filterwarnings = [
"ignore:.*does not have '__test__' attribute.*:UserWarning",
"ignore:.*does not have '__bases__' attribute.*:UserWarning",
]
[tool.typos.default]
extend-ignore-identifiers-re = [
".*_thw",
".*thw",
"ein",
".*arange",
".*MoBA",
".*temperal_downsample",
".*_nd",
".*nothink.*",
".*NOTHINK.*",
".*nin.*",
".*[Oo]no_[Aa]nna.*",
".*cann.*",
]
[tool.typos.default.extend-words]
ue = "ue"
semantics = "semantics"
fullset = "fullset"