Update README.md
#4
by
quazim
- opened
README.md
CHANGED
|
@@ -136,7 +136,6 @@ Benchmarking is one of the most important procedures during model acceleration.
|
|
| 136 |
|
| 137 |
### Latency benchmarks
|
| 138 |
|
| 139 |
-
TODO: UPLOAD BENCHS
|
| 140 |
__100 input/300 output; tok/s:__
|
| 141 |
|
| 142 |
| GPU/Model | S | M | L | XL | Original | W8A8, int8 |
|
|
|
|
| 136 |
|
| 137 |
### Latency benchmarks
|
| 138 |
|
|
|
|
| 139 |
__100 input/300 output; tok/s:__
|
| 140 |
|
| 141 |
| GPU/Model | S | M | L | XL | Original | W8A8, int8 |
|