AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[Docs] add note on fp16 in fast diffusion (#6380)

Browse Source 
add note on fp16
This commit is contained in:
Sayak Paul
2023-12-29 09:38:50 +05:30
committed by GitHub
parent e7044a4221
commit 203724e9d9
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/tutorials/fast_diffusion.md
View File

@@ -96,6 +96,8 @@ bfloat16 reduces the latency from 7.36 seconds to 4.63 seconds:
</div>
_(We later ran the experiments in float16 and found out that the recent versions of torchao do not incur numerical problems from float16.)_
**Why bfloat16?**
* Using a reduced numerical precision (such as float16, bfloat16) to run inference doesn’t affect the generation quality but significantly improves latency.