tanner/min-dalle-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

inplace attention state, faster and less memory

Browse Source
This commit is contained in:
Brett Kuprel
2022-07-04 09:14:37 -04:00
parent aca617dc64
commit 6f617fe98f
4 changed files with 25 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
Vendored
+1 -1
View File
@@ -9,7 +9,7 @@
This is a fast, minimal implementation of Boris Dayma's [DALL·E Mega](https://github.com/borisdayma/dalle-mini). It has been stripped down for inference and converted to PyTorch. The only third party dependencies are numpy, requests, pillow and torch.
It takes
- **35 seconds** to generate a 3x3 grid with a P100 in Colab
- **32 seconds** to generate a 3x3 grid with a P100 in Colab
- **16 seconds** to generate a 4x4 grid with an A100 on Replicate
- **TBD** to generate a 4x4 grid with an H100 (@NVIDIA?)