Skip to content

Commit

Permalink
[docs] fix table in fp16.mdx (huggingface#683)
Browse files Browse the repository at this point in the history
  • Loading branch information
NouamaneTazi authored Sep 30, 2022
1 parent 877bec8 commit daa2205
Showing 1 changed file with 10 additions and 33 deletions.
43 changes: 10 additions & 33 deletions docs/source/optimization/fp16.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -14,39 +14,16 @@ specific language governing permissions and limitations under the License.

We present some techniques and ideas to optimize 🤗 Diffusers _inference_ for memory or speed.

<table>
<tr>
<td>
<td>Latency
<td>Speedup
<tr>
<tr>
<td>original
<td>9.50s
<td>x1
<tr>
<tr>
<td>cuDNN auto-tuner
<td>9.37s
<td>x1.01
<tr>
<td>autocast (fp16)
<td>5.47s
<td>x1.91
<tr>
<td>fp16
<td>3.61s
<td>x2.91
<tr>
<td>channels last
<td>3.30s
<td>x2.87
<tr>
<tr>
<td>traced UNet
<td>3.21s
<td>x2.96
</table>

| | Latency | Speedup |
|------------------|---------|---------|
| original | 9.50s | x1 |
| cuDNN auto-tuner | 9.37s | x1.01 |
| autocast (fp16) | 5.47s | x1.91 |
| fp16 | 3.61s | x2.91 |
| channels last | 3.30s | x2.87 |
| traced UNet | 3.21s | x2.96 |

<em>obtained on NVIDIA TITAN RTX by generating a single image of size 512x512 from the prompt "a photo of an astronaut riding a horse on mars" with 50 DDIM steps.</em>

## Enable cuDNN auto-tuner
Expand Down

0 comments on commit daa2205

Please sign in to comment.