[project]
name = "semif-serve"
version = "0.1.4"
description = "HTTP wrapper around SemIf's direct and shared option-logit scorers"
requires-python = ">=3.12"
dependencies = [
  "fastapi==0.118.0",
  "uvicorn==0.37.0",
]

[project.optional-dependencies]
# The real engine. Pulls torch 2.10.0 (cu128) and transformers 5.17.0 through SemIf's exact pins.
model = [
  "semif-phase1 @ git+https://github.com/TheoLeeCJ/SemIf-OpenJev@23cf1f39fc9534fe81437200959b6dfc7106e45a",
  # Same pin SemIf declares, taken from the cu128 index: SemIf's committed predictions report
  # torch 2.10.0+cu128, and cu128 carries sm_120 kernels for the Blackwell cards.
  "torch==2.10.0",
]

# Qwen3.5's fast kernels. Without them transformers runs its reference PyTorch paths
# ("correct but much slower"). Trialled 2026-09-27; adopted only if parity with upstream holds.
fast = [
  "flash-linear-attention==0.5.2",
  "causal-conv1d @ https://github.com/Dao-AILab/causal-conv1d/releases/download/v1.7.0/causal_conv1d-1.7.0+cu12torch2.10cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; sys_platform == 'linux' and platform_machine == 'x86_64'",
]

[dependency-groups]
dev = ["pytest==8.4.2", "httpx==0.28.1"]

[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"

[tool.setuptools.packages.find]
where = ["src"]

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

[[tool.uv.index]]
name = "pytorch-cu128"
url = "https://download.pytorch.org/whl/cu128"
explicit = true

[tool.uv.sources]
torch = { index = "pytorch-cu128" }