[project]
name = "nanochat-inference-service"
version = "0.1.0"
description = "Standalone FastAPI inference service for nanochat"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
    "fastapi>=0.117.1",
    "filelock>=3.18.0",
    "huggingface_hub>=0.35.0",
    "pydantic-settings>=2.10.1",
    "requests>=2.32.0",
    "rustbpe>=0.1.0",
    "tiktoken>=0.11.0",
    "tokenizers>=0.22.0",
    "torch==2.9.1",
    "transformers>=4.57.3",
    "uvicorn>=0.36.0",
    "structlog>=24.4.0",
    "prometheus-fastapi-instrumentator>=7.0.0",
]

[dependency-groups]
dev = [
    "httpx>=0.28.1",
    "pytest>=8.0.0",
]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]

[tool.uv.sources]
torch = { index = "pytorch-cpu" }

[[tool.uv.index]]
name = "pytorch-cpu"
url = "https://download.pytorch.org/whl/cpu"
explicit = true