[RNE Rewrite] feat(models): add a Vulkan Supertonic variant - #1400
Closed
msluszniak wants to merge 2 commits into
Closed
[RNE Rewrite] feat(models): add a Vulkan Supertonic variant#1400msluszniak wants to merge 2 commits into
msluszniak wants to merge 2 commits into
Conversation
All four sub-models lower to Vulkan. On a Galaxy S26 Ultra (Adreno 840),
medians over interleaved rounds, at 512 text tokens and 1000 latent frames:
vulkan xnnpack
duration_predictor 18.7 33.2 1.78x
text_encoder 72.3 140.9 1.95x
vector_estimator 682.5 1253.7 1.84x
vocoder 865.8 1284.3 1.48x
2.12x end to end at the default 8 flow-matching steps, where vector_estimator
is 84% of the total. Outputs match the fp32 CPU references at cosine 1.000000,
0.999414, 0.999994 and 0.999977.
Vulkan leads BACKEND_ORDER.android, so this becomes the Android default.
textToSpeech now provisions vulkan in download-libs; without it the backend is
never downloaded and the model silently falls back to XNNPACK.
Needs the ExecuTorch fixes in pytorch/executorch#22399, #22401, #22402, #22403
and #22406, all cherry-picked into the labs fork and built into the 1.4.1
native libs.
Adds the Vulkan entry to the model picker and makes it the initial selection on Android, which is also what SUPERTONIC.DEFAULT resolves to there.
Member
Author
|
Folding these commits into #1392 instead. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Adds a Vulkan fp16 build of Supertonic, covering all four sub-models. Vulkan leads
BACKEND_ORDER.android, so this becomes the Android default formodels.textToSpeech.SUPERTONIC.Measured on a Galaxy S26 Ultra (Adreno 840), medians over interleaved rounds, at 512 text tokens and 1000 latent frames:
2.12x end to end at the default 8 flow-matching steps, where
vector_estimatoris 84% of the total. Outputs match the fp32 CPU references at cosine 1.000000, 0.999414, 0.999994 and 0.999977.textToSpeechnow provisionsvulkanin download-libs. Without it the backend is never downloaded and the model silently falls back to XNNPACK.Getting the model to lower correctly needed five ExecuTorch fixes, all open upstream and cherry-picked into the labs fork: pytorch/executorch#22399, #22401, #22402, #22403 and #22406. The Vulkan artifacts on the ExecuTorch 1.4.1 pre-release carry them.
Introduces a breaking change?
Type of change
Tested on
Testing instructions
apps/speechon an Android device.Related issues
Stacked on #1392.
Checklist