[Dev] Add VAE Inference Example#38
Open
themistbeforedawn wants to merge 1 commit into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
🗂️ PR Category
📝 Description
This PR only adds the WAN 2.2 VAE inference benchmark/example for measuring the performance impact of the optimization passes introduced in previous PRs.
The following numbers are CUDA HW sum averages over profiled iterations on the WAN 2.2 VAE 540p workload, measured on an NVIDIA H100 80G HBM3 GPU. Parentheses show MagiCompiler speedup over the corresponding baseline.
Decode
457.943 ms526.973 ms(1.15x)855.131 ms(1.87x)553.543 ms768.700 ms(1.39x)855.131 ms(1.54x)Encode
134.444 ms151.183 ms(1.12x)269.702 ms(2.01x)179.025 ms289.522 ms(1.62x)269.702 ms(1.51x)