Add Metal (Apple Silicon) build variants
#6
by
robtaylor-chipflow - opened
Add pre-built Metal kernel variants for Apple Silicon Macs.
Build variants:
torch210-metal-aarch64-darwintorch29-metal-aarch64-darwin
These enable GPU-accelerated rotary embedding on MPS (Metal Performance Shaders) backend, tested on M1/M2/M3/M4 with macOS 14+.
217/217 tests passing across all dtypes and configurations.