ao typo
#3
by
marksaroufim
- opened
README.md
CHANGED
@@ -129,7 +129,7 @@ CogVideoX is an open-source version of the video generation model originating fr
|
|
129 |
</tr>
|
130 |
<tr>
|
131 |
<td style="text-align: center;">Single GPU VRAM Consumption</td>
|
132 |
-
<td style="text-align: center;">FP16: 18GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>12.5GB* using diffusers</b><br><b>INT8: 7.8GB* using diffusers
|
133 |
<td style="text-align: center;">BF16: 26GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>20.7GB* using diffusers</b><br><b>INT8: 11.4GB* using diffusers with torchao</b></td>
|
134 |
</tr>
|
135 |
<tr>
|
|
|
129 |
</tr>
|
130 |
<tr>
|
131 |
<td style="text-align: center;">Single GPU VRAM Consumption</td>
|
132 |
+
<td style="text-align: center;">FP16: 18GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>12.5GB* using diffusers</b><br><b>INT8: 7.8GB* using diffusers with torchao</b></td>
|
133 |
<td style="text-align: center;">BF16: 26GB using <a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> / <b>20.7GB* using diffusers</b><br><b>INT8: 11.4GB* using diffusers with torchao</b></td>
|
134 |
</tr>
|
135 |
<tr>
|