Native Apple Metal GPU inference via mlx-c bindings
Find a file
Snider ff01175a62 bench(metal): add 29 benchmarks baselined on M3 Ultra
MatMul (128² to 4096², token projection), Softmax, element-wise
ops, fused Metal kernels (RMSNorm, LayerNorm, RoPE, SDPA), Linear,
Embedding, reductions, and full sampler chain. CGO floor ~170μs.

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 20:47:25 +00:00
cpp docs(cpp): complete mlx-c API research — all tasks done 2026-02-19 20:40:00 +00:00
docs/plans docs(plan): fold Virgil review into design and implementation plan 2026-02-19 19:25:05 +00:00
internal/metal bench(metal): add 29 benchmarks baselined on M3 Ultra 2026-02-19 20:47:25 +00:00
.gitignore chore: gitignore dist/ (CMake install output) 2026-02-19 19:30:23 +00:00
CLAUDE.md feat(api): migrate to go-inference shared interfaces 2026-02-19 20:15:42 +00:00
CMakeLists.txt feat: extract go-mlx from go-ai as standalone Metal inference package 2026-02-19 17:57:37 +00:00
FINDINGS.md bench(metal): add 29 benchmarks baselined on M3 Ultra 2026-02-19 20:47:25 +00:00
go.mod feat(api): migrate to go-inference shared interfaces 2026-02-19 20:15:42 +00:00
mlx.go feat(api): migrate to go-inference shared interfaces 2026-02-19 20:15:42 +00:00
mlx_stub.go feat: extract go-mlx from go-ai as standalone Metal inference package 2026-02-19 17:57:37 +00:00
mlx_test.go feat(api): migrate to go-inference shared interfaces 2026-02-19 20:15:42 +00:00
register_metal.go feat(metal): bind memory diagnostics and device info 2026-02-19 20:39:51 +00:00
TODO.md bench(metal): add 29 benchmarks baselined on M3 Ultra 2026-02-19 20:47:25 +00:00