[Feat]:Accelerate LightX2V using magi_compiler#1
Merged
Conversation
Collaborator
wtr0504
commented
Mar 25, 2026
wtr0504
commented
- Integrated MagiCompiler: Enabled inference acceleration on LightX2V for the Huanyuan1.5_480P_t2v_distill and Wan2.2 TI2V-5B models.
- Refactored TransformerInfer: Replaced certain components with native PyTorch operators to improve compatibility with Inductor for better performance. Also adjusted tensor shape transformations to make them more recognizable by TorchDynamo.
- Optimized ulysses_attn module: Modified parts of the implementation to eliminate graph breaks and improve compilation stability.
- Updated README.md: Added installation instructions for MagiCompiler along with detailed usage guidelines.
chore fix graph break in ulysses_attn Update README and requirements Update MagiCompiler Usage chore Update readme Fix transformer infer torch defaults and shape handling; update MagiCompiler install docs rm redundant code chore
wtr0504
force-pushed
the
dev/magi_compiler
branch
from
70596c5 to
7cd0c8e
Compare
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.