Metal Flash Attention for MLX — causal attention 1.5-2.9x faster than SDPA on Apple Silicon
Published
March 8, 2026
20h ago
Package Registry
README badge Customize →
License Sources Match
| Source | License | Class |
|---|---|---|
Licensie (detected) | MIT | Permissive |
PyPI (reported) | MIT | Permissive |
Loading dependencies…
License File
Added Removed Expected