Align batch handling for serving run and batched run #252
Conversation
This file contains 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
jonatanklosko
commented
Sep 21, 2023
Comment on lines
+107
to
+114
| if batch_size do | ||
| stream = | ||
| all_chunks | ||
| |> Stream.chunk_every(batch_size) | ||
| |> Stream.map(fn all_chunks -> | ||
| inputs = Bumblebee.Featurizer.process_input(featurizer, all_chunks) | ||
| Nx.Batch.concatenate([inputs]) | ||
| end) |
There was a problem hiding this comment.
@josevalim for now we still read the whole audio, but we chunk, so that the Bumblebee.Featurizer.process_input is called per batch, rather than for all chunks at once. I will later look at optimising ffmpeg to only decode chunk at a time.
josevalim
reviewed
Sep 25, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Uses the new
Nx.Serving.batch_size/2and also converts the input to a basic stream.