Skip to content

use softmax_last_dim (metal and cuda kernel) in llama attention layer… #321

use softmax_last_dim (metal and cuda kernel) in llama attention layer…

use softmax_last_dim (metal and cuda kernel) in llama attention layer… #321

Annotations

6 warnings

Check (ubuntu-latest, stable)

succeeded Oct 24, 2024 in 1m 21s