ywkang
372c987995
GEMM dimension reduction: - qkv_gemm.py: M,K,N = 128,256,128 → 32,64,32 (64 tiles → 1 tile). - qkv_gemm_multi_pe.py: same reduction. - Tests verify pipeline correctness, not large-matrix throughput. - Per-test time: 18s → 1.7s. 6 tests total: 108s → 10s. pytest-xdist parallel execution: - Add pytest-xdist to dev dependencies. - pyproject.toml addopts: -n auto (use all CPU cores), -m "not slow". - Default `pytest` runs 501 tests in ~12s (previously 148s). - Full suite including slow: `pytest -m ""` → 3m24s (previously 5m43s). pytest.mark.slow: - Registered in pyproject.toml markers section. - 256-rank full-system test is the only slow-marked test. - Run with: pytest -m "" (CI) or pytest (local dev, skips slow). 502 tests pass. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
37 lines
871 B
TOML
37 lines
871 B
TOML
[build-system]
|
|
requires = ["setuptools>=68", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "kernbench"
|
|
version = "0.1.0"
|
|
requires-python = ">=3.10"
|
|
dependencies = ["pytest", "simpy", "pyyaml", "fastapi>=0.110", "uvicorn[standard]>=0.29", "websockets>=12", "numpy>=1.24", "greenlet>=3.0"]
|
|
|
|
[project.scripts]
|
|
kernbench = "kernbench.cli.main:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["src", "."]
|
|
include = ["kernbench*", "benches*"]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=7",
|
|
"pytest-xdist>=3.0",
|
|
"ruff>=0.4.0",
|
|
]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py310"
|
|
fix = false
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "B", "UP"]
|
|
ignore = ["F401"]
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = ["--disable-warnings", "-n", "auto", "-m", "not slow"]
|
|
markers = ["slow: 256-rank full-system tests (~3min each, run with: pytest -m '')"]
|