Four jobs, all fast, all free on public repos:
- engine: make glm + make test-c (Linux, CPU, native arch)
- engine-cuda-syntax: nvcc compile-only check (no GPU needed, catches
backend_cuda.cu syntax/type errors before they reach a real machine)
- web: npm ci + build + vitest (Node 22, cached deps)
- python: unittest discover on c/tests/test_*.py (Python 3.12)
Triggers on push/PR to dev and main. No 20-minute pipelines — the whole
matrix finishes in under 3 minutes on GitHub-hosted runners.