Lev Novitskiy
Lev Novitskiy
Hey again! Now my Floyd-Warshall algorithm is optimised! https://github.com/leffff/graphormer-pyg/commit/c9b13f6542a79e4a2f4f46a5b35b3c08924565ee
Fixed Centrality Encoding! Rewritten from cycles to PyG utils! https://github.com/leffff/graphormer-pyg/commit/e7772c834600ec2773dc2cc703e2a847260a0900
The repository still has a [list of optimizations](https://github.com/leffff/graphormer-pyg/issues) to complete! Anyone is more than welcome to contribute!
Hi! We have a MagCache version in our main repo. @sayakpaul hiw can we integrate MagCache into Diffusers pipeline?
Hi! I See the problem. If you have fixes you want to propose please create a pull request. However, does Flex Attention work fine on non Cuda systems?
When you open the PR, plz tag me and provide examples Of before/after generations from the same noise,so we make sure the results are stable.
Hi @AlanPonnachan @sayakpaul The thing with MagCache is it requires precomputing magnitudes. @AlanPonnachan has done it for Flux, but how will this work for other models?
@AlanPonnachan ?
> @leffff , Thank you for your review. > > To address this, I am implementing a **Calibration Mode**. > > My plan is to add a `calibrate=True` flag to...
Looks Great! Could you please provide a usage example: 1. import & load a specific model 2. Inference 3. Calibrate 4. Inference w MagCahce And Provide Generations To be Sure...