Skip to content

Commit 14df270

Browse files
authored
Update README.md
1 parent c5d3454 commit 14df270

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

README.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -72,6 +72,7 @@ Benchmarks run on an 8xA100-80GB, power limited to 330W with a hybrid cube mesh
7272

7373
### Tensor Parallelism + Quantization
7474
| Model | Technique | Tokens/Second | Memory Bandwidth (GB/s) |
75+
| -------- | ------- | ------ | ------ |
7576
| Llama-2-70B | Base | 62.50 | 1135.29 |
7677
| | 8-bit | 80.44 | 752.04 |
7778
| | 4-bit (G=32) | 90.77 | 548.10 |

0 commit comments

Comments
 (0)