Skip to content

[docs] fix table in fp16.mdx #683

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pcuenca merged 1 commit into from
Sep 30, 2022
Merged

[docs] fix table in fp16.mdx #683

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 10 additions & 33 deletions docs/source/optimization/fp16.mdx
View file
Open in desktop
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