Repository navigation
feat(inference): opt-in fused Snake CUDA decoder - #538
Open
zain1806481 wants to merge 1 commit into
Open
zain1806481 wants to merge 1 commit into
zain1806481 wants to merge 1 commit into
Conversation
Copy link
Copy Markdown
Sorry, something went wrong.
Add KOKORO_DECODER_FUSION=1 path that freezes weight-norm layers and replaces AdaIN residual Snake activations with one NVRTC FP32 kernel. Fails closed without CUDA/NVRTC; no CPU fallback. Measured ~8.5% faster with exact audio on Quadro K620 (sm_50). Co-authored-by: Cursor <cursoragent@cursor.com>
Copy link
Copy Markdown
Author
|
Supporting notes for this PR:
Fusion remains opt-in via KOKORO_DECODER_FUSION=1 and fails closed without CUDA/NVRTC. |
Sorry, something went wrong.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Measured (Quadro K620, sm_50)
Alternating original/fused on the same frozen-weight model, fixed seed:
Other GPUs may work (kernel targets the current device arch) but were not the validation target.
Test plan
Made with Cursor