From 2c60a442f34e4edcb009e022ed4af6d851094edb Mon Sep 17 00:00:00 2001
From: Manuel de Prada Corral <6536835+manueldeprada@users.noreply.github.com>
Date: Mon, 21 Apr 2025 18:01:11 +0200
Subject: [PATCH] fix link in kv_cache.md (#37652)

fix typo in kv_cache.md
---
 docs/source/en/kv_cache.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/source/en/kv_cache.md b/docs/source/en/kv_cache.md
index 36f82fb3dc..36a3d69d64 100644
--- a/docs/source/en/kv_cache.md
+++ b/docs/source/en/kv_cache.md
@@ -18,7 +18,7 @@ rendered properly in your Markdown viewer.
 
 The key-value (KV) vectors are used to calculate attention scores. For autoregressive models, KV scores are calculated *every* time because the model predicts one token at a time. Each prediction depends on the previous tokens, which means the model performs the same computations each time.
 
-A KV *cache* stores these calculations so they can be reused without recomputing them. Efficient caching is crucial for optimizing model performance because it reduces computation time and improves response rates. Refer to the [Caching](./cache_explanation.md) doc for a more detailed explanation about how a cache works.
+A KV *cache* stores these calculations so they can be reused without recomputing them. Efficient caching is crucial for optimizing model performance because it reduces computation time and improves response rates. Refer to the [Caching](./cache_explanation) doc for a more detailed explanation about how a cache works.
 
 Transformers offers several [`Cache`] classes that implement different caching mechanisms. Some of these [`Cache`] classes are optimized to save memory while others are designed to maximize generation speed. Refer to the table below to compare cache types and use it to help you select the best cache for your use case.