mirror of
https://github.com/ml-explore/mlx.git
synced 2025-09-24 06:28:08 +08:00
1865299a30
* Metal shaders for efficient self attention on large sequences Updated fast attention: GEMM-ified with Steel primitives Uses flash attention 1 for scale correction * more compiler silencing * Address rebase issues * Templatize kernel instantiation, revise cpu bindings * Safer writes to output * Permit batch size > 1 * Numerical fixes for sdpa self attention * Re-enable test, remove unused variable * add benchmarking script * Disable sdpa prior to perf tuning, and simplify tests for per-patch CI