Optimizing the Performance of Decoder fl_asr_decode
#709
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Outdated suggestions cannot be applied.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.
Original Issue: #707
Summary
This pull request improves the performance of the decoder (
fl_asr_decode
), targeting the transformer model, by offering the following optimizations:Test Plan (required)
Using the following flag file, the average decoding time on V100 can be improved by more that 4X using the optimizations that this pull request offers. The custom kernel for positional embedding may also improve the training performance. However, the impact is not measured.