Update README.md

Author: DefTruth

README.md

@@ -20,7 +20,7 @@
   <img src='https://github.com/user-attachments/assets/c7d65fe5-9fb9-49a8-b962-a6c09bcc030a' height="225px" width="400px">
 </div> 
 
-Currently, on NVIDIA L20, RTX 4090 and RTX 3090 Laptop, compared with cuBLAS's default Tensor Cores math algorithm `CUBLAS_GEMM_DEFAULT_TENSOR_OP`, the `HGEMM (WMMA/MMA)` implemented in this repo(`light blue`) can achieve `95%~98%` of its(`orange`) performance. Please check [hgemm benchmark](./hgemm) for more details.
+Currently, on NVIDIA L20, RTX 4090 and RTX 3090 Laptop, compared with cuBLAS's default Tensor Cores math algorithm `CUBLAS_GEMM_DEFAULT_TENSOR_OP`, the `HGEMM (WMMA/MMA)` implemented in this repo(`light blue`) can achieve `95%~99%` of its(`orange`) performance. Please check [hgemm benchmark](./hgemm) for more details.
 
 |CUDA Cores|Sliced K(Loop over K)|Tile Block|Tile Thread|
 |:---:|:---:|:---:|:---:|