Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "7b3a4bcc8d64bbcd36791c2f21d2c16e51bebb74"
Commit b92f2c3b authored by Tri Dao's avatar Tri Dao
Browse files

Link to Colossal-AI's stable diffusion in usage.md

parent 343492ec
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 0 deletions
usage.md
View file @ b92f2c3b
...@@ -59,6 +59,11 @@ yields the fastest BERT training on cloud instances in MLPerf training 2.0 (June ...@@ -59,6 +59,11 @@ yields the fastest BERT training on cloud instances in MLPerf training 2.0 (June
v0.7.0](https://github.com/huggingface/diffusers/releases/tag/v0.7.0). v0.7.0](https://github.com/huggingface/diffusers/releases/tag/v0.7.0).
Up to 2x faster inference and lower memory usage. Up to 2x faster inference and lower memory usage.
- Colossal-AI's
[implementation](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion)
of Stable Diffusion: with FlashAttention as one of its components, it speeds up
pretraining by up to 6.5x, and reduces the hardware cost of fine-tuning by 7x.
- Stable Diffusion inference from - Stable Diffusion inference from
[Labml.ai](https://twitter.com/labmlai/status/1573634095732490240): 50% speedup. [Labml.ai](https://twitter.com/labmlai/status/1573634095732490240): 50% speedup.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment