tflops fix

Author: LeiWang1999

benchmark/matmul_fp8/README.md

@@ -27,10 +27,10 @@ PY
 
 | K     | Latency (s) | Throughput (TFLOPs) |
 |-------|-------------|---------------------|
-|   256 | 0.091488    | 0.376               |
-|   512 | 0.110496    | 0.622               |
-|  1024 | 0.148256    | 0.927               |
-|  2048 | 0.234080    | 1.174               |
-|  4096 | 0.398944    | 1.378               |
-|  8192 | 0.752416    | 1.461               |
-| 16384 | 1.443808    | 1.523               |
+|   256 | 0.091488    | 376                 |
+|   512 | 0.110496    | 622                 |
+|  1024 | 0.148256    | 927                 |
+|  2048 | 0.234080    | 1174                |
+|  4096 | 0.398944    | 1378                |
+|  8192 | 0.752416    | 1461                |
+| 16384 | 1.443808    | 1523                |