inference-engine-benchmark-system/pyproject.toml at main · varad-more/inference-engine-benchmark-system · 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
116
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "inference-engine-benchmark"
version = "1.0.0"
description = "Comparative benchmark system for vLLM vs SGLang inference engines"
readme = "README.md"
requires-python = ">=3.11"
license = { text = "MIT" }
license-files = ["LICENSE"]

dependencies = [
    "httpx>=0.27.0",
    "pydantic>=2.7.0",
    "structlog>=24.1.0",
    "asyncio-throttle>=1.0.2",
    "numpy>=1.26.0",
    "fastapi>=0.111.0",
    "uvicorn[standard]>=0.30.0",
    "websockets>=12.0",
    "typer>=0.12.0",
    "rich>=13.7.0",
    "matplotlib>=3.9.0",
    "jinja2>=3.1.4",
    "aiofiles>=23.2.1",
    "python-multipart>=0.0.9",
]

[project.optional-dependencies]
sglang = [
    "sglang>=0.3.0",
]
dev = [
    "pytest>=8.2.0",
    "pytest-asyncio>=0.23.0",
    "pytest-httpx>=0.30.0",
    "respx>=0.21.0",
    "mypy>=1.10.0",
    "ruff>=0.4.0",
    "build>=1.2.2",
    "twine>=5.1.1",
]

[project.scripts]
benchmark = "run_experiment:app"

[tool.ruff]
line-length = 100
target-version = "py311"

[tool.ruff.lint]
select = ["E", "F", "I", "UP"]

[tool.ruff.lint.per-file-ignores]
# Files with long embedded strings (HTML, SVG, regex, test fixtures)
"analysis/generate_final_benchmark_report.py" = ["E501"]
"analysis/report.py" = ["E501"]
"dashboard/app.py" = ["E501"]
"analysis/final_report.py" = ["E501"]
"analysis/decode_length_analysis.py" = ["E501"]
"analysis/goodput.py" = ["E501"]
"analysis/tpot_analysis.py" = ["E501"]
"analysis/variance_analysis.py" = ["E501"]
"analysis/generate_spec_decoding_figure.py" = ["E501"]
"analysis/generate_decode_length_figure.py" = ["E501"]
"analysis/generate_variance_figure.py" = ["E501"]
"analysis/generate_goodput_figure.py" = ["E501"]
"benchmarks/metrics.py" = ["E501"]
"benchmarks/runner.py" = ["E501"]
"benchmarks/scenarios.py" = ["E501"]
"run_experiment.py" = ["E501"]
"tests/test_dashboard.py" = ["E501"]

[tool.ruff.format]
exclude = ["analysis/generate_final_benchmark_report.py"]

[tool.mypy]
python_version = "3.11"
ignore_missing_imports = true
warn_redundant_casts = true
warn_unused_configs = true
show_error_codes = true

[[tool.mypy.overrides]]
module = ["analysis.generate_final_benchmark_report"]
ignore_errors = true

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

[tool.hatch.build.targets.wheel]
packages = ["engines", "benchmarks", "dashboard", "sglang_programs", "analysis"]
include = ["run_experiment.py", "prompts/**"]

[tool.hatch.build.targets.sdist]
include = [
    "engines/**",
    "benchmarks/**",
    "dashboard/**",
    "sglang_programs/**",
    "analysis/**",
    "tests/**",
    "deploy/**",
    "prompts/**",
    "run_experiment.py",
    "docker-compose.yml",
    "Dockerfile.dashboard",
    "README.md",
    "LICENSE",
    "pyproject.toml",
    ".env.example",
    "docs/**",
]