Fuse LayerNorm modulation into Triton kernel and remove RoPE dtype casts#133
Open
Jordanyang wants to merge 1 commit into
Open
Fuse LayerNorm modulation into Triton kernel and remove RoPE dtype casts#133Jordanyang wants to merge 1 commit into
Jordanyang wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
FastLayerNorm.modulate.Motivation
This reduces extra dtype conversion overhead around RoPE and moves the modulation step into the fused LayerNorm kernel path, avoiding separate scale/shift operations after normalization.
Changes
turbodiffusion/ops/core.pyto support fused LayerNorm modulation.turbodiffusion/rcm/networks/wan2pt1.pyto use the fused modulation path and remove RoPE dtype casts.turbodiffusion/rcm/networks/wan2pt2.pyto use the same fused modulation path and remove RoPE dtype casts.Validation