Translation
ExecuTorch
msluszniak's picture
Unpublish variants that lose on device
9ae5659 verified
|
Raw History Blame Contribute Delete
169 Bytes
Exported and not published. On an iPhone 16 MLX decodes at 3.2 ms/step (int8) and
3.9 ms/step (bf16) against 1.95 ms for XNNPACK int8, at the same BLEU. Use `xnnpack/`.