Commit Graph

4 Commits

Author SHA1 Message Date
Binyang Li
eeea00b298 Support python wheel build (#787)
## Support Python wheel build

This PR modernizes the Python packaging for MSCCL++ by defining
dependencies and optional extras in `pyproject.toml`, enabling proper
wheel builds with `pip install ".[cuda12]"`.

### Changes

**`pyproject.toml`**
- Add `dependencies` (numpy, blake3, pybind11, sortedcontainers)
- Add `optional-dependencies` for platform-specific CuPy (`cuda11`,
`cuda12`, `cuda13`, `rocm6`), `benchmark`, and `test` extras
- Bump minimum Python version from 3.8 to 3.10

**`test/deploy/setup.sh`**
- Use `pip install ".[<platform>,benchmark,test]"` instead of separate
`pip install -r requirements_*.txt` + `pip install .` steps
- Add missing CUDA 13 case

**`docs/quickstart.md`**
- Update install instructions to use extras (e.g., `pip install
".[cuda12]"`)
- Document all available extras and clarify that `rocm6` builds CuPy
from source
- Update Python version references to 3.10

**`python/csrc/CMakeLists.txt`**, **`python/test/CMakeLists.txt`**
- Update `find_package(Python)` from 3.8 to 3.10

### Notes
- The `requirements_*.txt` files are kept for Docker base image builds
where only dependencies (not the project itself) should be installed.
- CuPy is intentionally not in base dependencies — users must specify a
platform extra to get the correct pre-built wheel (or source build for
ROCm).

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-04-16 21:24:45 -07:00
Binyang Li
8896cd909a Add ROCm FP8 E4M3B15 support (#774)
## Summary

Add ROCm (gfx942) support for the FP8 E4M3B15 data type, including
optimized conversion routines between FP8 E4M3B15 and FP16/FP32 using
inline assembly.

Extends the allpair packet and fullmesh allreduce kernels to support
higher-precision accumulation (e.g., FP16/FP32) when reducing FP8 data,
improving numerical accuracy.

Adds Python tests to verify that higher-precision accumulation is at
least as accurate as native FP8 accumulation across all algorithm
variants.

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-04-08 09:53:45 -07:00
Binyang Li
c12822a7af create CI pipeline for rocm (#718)
Create CI pipeline for AMD GPU.
2026-02-09 16:55:16 -08:00
Binyang Li
0c7311e83f Add CI for rocm (#346) 2024-09-15 22:30:54 +00:00