Native Apple Metal GPU inference via mlx-c bindings
c96f9bd006
1. Error handler thread safety: last_mlx_error now uses _Atomic(const char*) with atomic_store_explicit/atomic_exchange_explicit (release/acquire). 2. macOS version minimum: -mmacosx-version-min changed from 26.0 to 13.3 (MLX's own minimum), no longer locks out macOS 14/15 users. 3. LoadOption applied in metalBackend.LoadModel(): calls ApplyLoadOpts(), passes ContextLen through to Model which replaces unbounded KVCache with RotatingKVCache when set. GPULayers=0 logs a warning. Co-Authored-By: Virgil <virgil@lethean.io> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| cpp | ||
| docs/plans | ||
| internal/metal | ||
| .gitignore | ||
| CLAUDE.md | ||
| CMakeLists.txt | ||
| FINDINGS.md | ||
| go.mod | ||
| mlx.go | ||
| mlx_stub.go | ||
| mlx_test.go | ||
| register_metal.go | ||
| TODO.md | ||