mirror of
https://github.com/cloudstack-llc/mlx-knife.git
synced 2026-07-15 04:46:32 -04:00
The BROKE Team
74239c4e43
Issues Resolved: • Issue #15: Token limits vs natural stop tokens race condition - FIXED • Issue #16: Interactive vs server token limit policies - FIXED Major Improvements: • Automatic optimal token limits - no configuration needed • Manual --max-tokens control still available when desired • Eliminates old hardcoded 500/2000 token restrictions • Performance gains: Up to 524x improvement for large context models • Enhanced web client with model capabilities display and better UX Additional Enhancements: • Enhanced /v1/models API with context_length field • Comprehensive test expansion: 114 → 131 tests (131/131 passing) • Python 3.9-3.13 compatibility verified Known Issues (Beta Status): • Server deadlock possible under extreme concurrent model loading stress • Workaround: Avoid simultaneous heavy model operations
154 lines
3.9 KiB
TOML
154 lines
3.9 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "mlx-knife"
|
|
dynamic = ["version"]
|
|
description = "ollama-style CLI for MLX models on Apple Silicon"
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
license = {text = "MIT"}
|
|
authors = [
|
|
{name = "The BROKE team", email = "broke@gmx.eu"},
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Intended Audience :: Developers",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.9",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Operating System :: MacOS",
|
|
"Environment :: Console",
|
|
]
|
|
dependencies = [
|
|
"huggingface-hub>=0.34.0",
|
|
"requests>=2.32.0",
|
|
"mlx>=0.28.0",
|
|
"mlx-lm>=0.26.0",
|
|
"fastapi>=0.116.0",
|
|
"uvicorn>=0.35.0",
|
|
"pydantic>=2.11.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
test = [
|
|
"pytest>=7.4.0",
|
|
"pytest-asyncio>=0.21.0",
|
|
"pytest-timeout>=2.1.0",
|
|
"psutil>=5.9.0",
|
|
"pytest-mock>=3.11.0",
|
|
"pytest-cov>=4.1.0"
|
|
]
|
|
dev = [
|
|
"ruff>=0.1.0",
|
|
"mypy>=1.7.0",
|
|
"types-requests>=2.31.0"
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/mzau/mlx-knife"
|
|
Issues = "https://github.com/mzau/mlx-knife/issues"
|
|
|
|
[project.scripts]
|
|
mlxk = "mlx_knife.cli:main"
|
|
mlx-knife = "mlx_knife.cli:main"
|
|
mlx_knife = "mlx_knife.cli:main"
|
|
|
|
[tool.setuptools]
|
|
packages = ["mlx_knife"]
|
|
|
|
[tool.setuptools.dynamic]
|
|
version = {attr = "mlx_knife.__version__"}
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
python_files = "test_*.py"
|
|
python_classes = "Test*"
|
|
python_functions = "test_*"
|
|
addopts = [
|
|
"-v",
|
|
"--tb=short",
|
|
"--strict-markers",
|
|
"--disable-warnings",
|
|
"--durations=10",
|
|
"-m not server"
|
|
]
|
|
markers = [
|
|
"integration: integration tests (slower)",
|
|
"unit: unit tests (faster)",
|
|
"slow: slow running tests",
|
|
"requires_model: tests that need actual MLX models",
|
|
"network: tests that require network access",
|
|
"server: tests that require MLX Knife server with loaded models (manual setup required)"
|
|
]
|
|
timeout = 300
|
|
norecursedirs = [".git", ".tox", "dist", "build", "*.egg", "venv", "__pycache__"]
|
|
minversion = "6.0"
|
|
|
|
[tool.ruff]
|
|
target-version = "py39"
|
|
line-length = 88
|
|
extend-exclude = [
|
|
".git",
|
|
"__pycache__",
|
|
"venv*",
|
|
".venv",
|
|
"build",
|
|
"dist"
|
|
]
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"E", # pycodestyle errors
|
|
"W", # pycodestyle warnings
|
|
"F", # pyflakes
|
|
"I", # isort
|
|
"B", # flake8-bugbear
|
|
"C4", # flake8-comprehensions
|
|
"UP", # pyupgrade
|
|
]
|
|
ignore = [
|
|
"E501", # line too long (handled by formatter)
|
|
"B008", # do not perform function calls in argument defaults
|
|
# Python 3.9 compatibility policy - keep legacy typing for maximum compatibility
|
|
"UP006", # Use list instead of List (keep typing.List for Python 3.9 compat)
|
|
"UP035", # typing.Dict is deprecated (keep typing.Dict for Python 3.9 compat)
|
|
# Temporary ignores for release - TODO: fix these in future versions
|
|
"E402", # Module level import not at top of file
|
|
"E722", # Do not use bare except
|
|
"W293", # Blank line contains whitespace
|
|
"C414", # Unnecessary list() call
|
|
"B904", # Exception handling (raise from)
|
|
]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"tests/*" = ["B011"] # assert False in tests is ok
|
|
|
|
[tool.mypy]
|
|
python_version = "3.9"
|
|
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
|
|
show_error_codes = true
|
|
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"mlx.*",
|
|
"mlx_lm.*",
|
|
"huggingface_hub.*"
|
|
]
|
|
ignore_missing_imports = true |