From 72fe3f8e3df827fa19ecf66f7298f30a995bb46e Mon Sep 17 00:00:00 2001 From: NanoCode012 Date: Tue, 15 Aug 2023 22:40:52 +0900 Subject: [PATCH] Fix(docs): Update flash attn requirements (#409) --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 403cae4d6..8c3f9adb4 100644 --- a/README.md +++ b/README.md @@ -483,8 +483,8 @@ max_grad_norm: flash_optimum: # whether to use xformers attention patch https://github.com/facebookresearch/xformers: xformers_attention: -# whether to use flash attention patch https://github.com/HazyResearch/flash-attention: -flash_attention: # require a100 for llama +# whether to use flash attention patch https://github.com/Dao-AILab/flash-attention: +flash_attention: # whether to use scaled-dot-product attention # https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html sdp_attention: