Tom Foster
86e9de9e75
All checks were successful
Build Vast.ai Ollama Benchmark Image / Build and Push (push) Successful in 4m43s
111 lines
3.1 KiB
TOML
111 lines
3.1 KiB
TOML
[project]
|
|
name = "gpu-llm-benchmarking"
|
|
version = "0.1.0"
|
|
description = "Benchmarking tool for testing LLM inference performance across different context window sizes on various GPUs."
|
|
readme = "README.md"
|
|
license = { text = "Apache-2.0" }
|
|
authors = [{ name = "Tom Foster", email = "tom@tomfos.tr" }]
|
|
maintainers = [{ name = "Tom Foster", email = "tom@tomfos.tr" }]
|
|
requires-python = ">=3.11"
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Topic :: System :: Benchmark",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
]
|
|
dependencies = [
|
|
"paramiko>=3",
|
|
"python-dotenv>=1",
|
|
"requests>=2",
|
|
"vastai-sdk>=0",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://git.tomfos.tr/tom/gpu-llm-benchmarking"
|
|
"Bug Reports" = "https://git.tomfos.tr/tom/gpu-llm-benchmarking/issues"
|
|
"Source" = "https://git.tomfos.tr/tom/gpu-llm-benchmarking"
|
|
|
|
[dependency-groups]
|
|
dev = ["ruff>=0", "uv>=0", "mypy>=1", "types-requests>=2", "types-paramiko>=3"]
|
|
|
|
[tool.uv]
|
|
package = true
|
|
|
|
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project.scripts]
|
|
benchmark-llm = "scripts.llm_benchmark:main"
|
|
|
|
[tool.setuptools]
|
|
packages = { find = {} }
|
|
|
|
[tool.ruff]
|
|
cache-dir = "/tmp/.ruff_cache"
|
|
fix = true
|
|
line-length = 100
|
|
preview = true
|
|
show-fixes = false
|
|
target-version = "py311"
|
|
unsafe-fixes = true
|
|
|
|
[tool.ruff.format]
|
|
line-ending = "auto"
|
|
skip-magic-trailing-comma = false
|
|
|
|
[tool.ruff.lint]
|
|
fixable = ["ALL"]
|
|
ignore = [
|
|
"ANN401", # use of Any type
|
|
"BLE001", # blind Exception usage
|
|
"COM812", # missing trailing comma
|
|
"CPY", # flake8-copyright
|
|
"FBT", # boolean arguments
|
|
"PLR0912", # too many branches
|
|
"PLR0913", # too many arguments
|
|
"PLR0915", # too many statements
|
|
"PLR0917", # too many positional arguments
|
|
"PLR6301", # method could be static
|
|
"RUF029", # async methods that don't await
|
|
"S104", # binding to all interfaces
|
|
"S110", # passed exceptions
|
|
"S404", # subprocess module usage (needed for nvidia-smi)
|
|
"S602", # subprocess with shell=True
|
|
"S603", # subprocess.run(check=False)
|
|
"S607", # starting process with partial path
|
|
"TRY301", # raise inside try block
|
|
]
|
|
select = ["ALL"]
|
|
unfixable = [
|
|
"F841", # local variable assigned but never used
|
|
"RUF100", # unused noqa comments
|
|
"T201", # don't strip print statement
|
|
]
|
|
|
|
[tool.ruff.lint.isort]
|
|
combine-as-imports = true
|
|
required-imports = ["from __future__ import annotations"]
|
|
|
|
[tool.ruff.lint.pydocstyle]
|
|
convention = "google"
|
|
|
|
[tool.mypy]
|
|
python_version = "3.11"
|
|
warn_return_any = true
|
|
warn_unused_configs = true
|
|
disallow_untyped_defs = false
|
|
disallow_incomplete_defs = false
|
|
check_untyped_defs = true
|
|
disallow_untyped_decorators = false
|
|
no_implicit_optional = true
|
|
warn_redundant_casts = true
|
|
warn_unused_ignores = true
|
|
warn_no_return = true
|
|
follow_imports = "normal"
|
|
ignore_missing_imports = true
|