Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
epwalsh authored Oct 23, 2024
1 parent 310866e commit 0f0d282
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ Throughput numbers from these scripts with various different configuration setti
| | 4096 | BF16/FP8[^2] | 5,500 TPS | `OLMo-13B.py` | `--model.float8_config.enabled=true` |

[^1]: Throughput reported in tokens per second per device.
[^2]: In this setup most GEMMs are computed in `float8`, everything else is in `bfloat16`.
[^2]: In this setup most matrix multiplications are computed in `float8`, everything else is in `bfloat16`.

## Development

Expand Down

0 comments on commit 0f0d282

Please sign in to comment.