From e6bcdc60cf5ad328dd5adbe1376d2f56c114dcb0 Mon Sep 17 00:00:00 2001
From: Yang Wang <3883941+YangWang92@users.noreply.github.com>
Date: Fri, 20 Nov 2020 13:46:54 +0800
Subject: [PATCH] fix broken links (#148)

---
 media/docs/implicit_gemm_convolution.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/media/docs/implicit_gemm_convolution.md b/media/docs/implicit_gemm_convolution.md
index 34102918..c86d41df 100644
--- a/media/docs/implicit_gemm_convolution.md
+++ b/media/docs/implicit_gemm_convolution.md
@@ -165,7 +165,7 @@ This enables 128-bit vector memory acceses which lead to efficient CUDA kernels.
 CUTLASS defines CUDA C++ templates accepting numerous template arguments to specialize the resulting
 kernel by operation, data type, tile configuration, math instruction, and fused output operation.
 
-In [09_turing_tensorop_conv2dfprop.cu](/examples/09_turing_tensorop_conv2dfprop/09_turing_tensorop_conv2dfprop.cu), a convolution
+In [turing_tensorop_conv2dfprop.cu](/examples/09_turing_tensorop_conv2dfprop/turing_tensorop_conv2dfprop.cu), a convolution
 operation is defined as follows.
 
 ```c++