Kilian Haefeli

icon location Studying ML and DL at ETH Zurich | Previously Large Language Models at @AlephAlpha and Data Science at @Logitech and Cofounder @Airica

Results 1 issues of Kilian Haefeli

Flashattention

9 comment

## Faster Flash Attention Implementation Added `attention_forward6` to `src/attention_forward`: A fast flash attention forward pass to `src/attention_forward` written without any dependencies. We are assuming using a causal mask here. This...