From 01a4c3d82a53dd26b0fea21ad8ecd39c342fc766 Mon Sep 17 00:00:00 2001 From: Haoliang Zhang Date: Wed, 5 Jun 2024 09:39:49 -0700 Subject: [PATCH] Update README.md (#31) BUG=none --- ai_edge_torch/generative/layers/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ai_edge_torch/generative/layers/README.md b/ai_edge_torch/generative/layers/README.md index 78d64188..e90cefd0 100644 --- a/ai_edge_torch/generative/layers/README.md +++ b/ai_edge_torch/generative/layers/README.md @@ -43,4 +43,4 @@ Currently, the library provides the following configuration class for you to cus ## High-Level function boundary for performance We introduce High-Level Function Boundary (HLFB) as a way of annotating performance-critical pieces of the model (e.g. `scaled_dot_product_attention`, or `KVCache`). HLFB allows the converter to lower the annotated blocks to performant TFLite custom ops. Following is an example of applying HLFB to `SDPA`: -https://github.com/google-ai-edge/ai-edge-torch/blob/853301630f2b2455bd2e2f73d8a47e1a1534c91c/ai_edge_torch/generative/layers/attention.py#L74-L122 +https://github.com/google-ai-edge/ai-edge-torch/blob/25c764ad21e6f1fda5600dfc27406ef0424c8c3a/ai_edge_torch/generative/layers/scaled_dot_product_attention.py#L69-L117