Replace torch CUDAExtension/ParallelBuildExtension with a CMake-based build. Each kernel compiles as an independent pybind11 module in parallel via cmake --build -j, outputting to astrai/extension/lib. - Add csrc/CMakeLists.txt (5 kernel targets, torch/pybind11 linking) - setup.py: _CMakeBuildExt invokes cmake; auto-detect CUDA arch via torch - Remove csrc/build.py (REGISTRY/build flags now in CMakeLists) - Fix rel-err eps in attn_test.cu (1e-8 -> 1e-4, bf16 scale) - Update docs/developer/cuda_kernels.md build section - .gitignore: allow csrc/CMakeLists.txt
38 lines
543 B
Plaintext
38 lines
543 B
Plaintext
# Ignore everything
|
|
*
|
|
|
|
# Allow directories to be traversed
|
|
!*/
|
|
|
|
# Allow specific file types and root files
|
|
!astrai/**/*.py
|
|
!scripts/**/*.py
|
|
!tests/**/*.py
|
|
!csrc/**/*.py
|
|
!csrc/CMakeLists.txt
|
|
|
|
!csrc/**/*.cu
|
|
!csrc/**/*.h
|
|
!csrc/**/*.cuh
|
|
|
|
!scripts/**/*.sh
|
|
|
|
# Allow GitHub files
|
|
!/.github/**
|
|
|
|
# Allow root files
|
|
!/.gitattributes
|
|
!/.dockerignore
|
|
!/Dockerfile
|
|
!/docker-compose.yml
|
|
!/docs/**
|
|
!/CONTRIBUTING.md
|
|
!/LICENSE
|
|
!/pyproject.toml
|
|
!/README.md
|
|
# Allow extension modules (only source .py)
|
|
!/astrai/extension/**/*.py
|
|
|
|
# Allow build files
|
|
!/setup.py
|