diff --git a/docs/source/optimization/fp16.mdx b/docs/source/optimization/fp16.mdx index bb58c19b49a4..01de1c01b339 100644 --- a/docs/source/optimization/fp16.mdx +++ b/docs/source/optimization/fp16.mdx @@ -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. - - - - - - - - - - - -
- 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 -
+ +| | 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 | + 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. ## Enable cuDNN auto-tuner