Fix CUDA OOM on long scripts by splitting input into chunks#158
Open
rachana192837 wants to merge 1 commit intomicrosoft:mainfrom
Open
Fix CUDA OOM on long scripts by splitting input into chunks#158rachana192837 wants to merge 1 commit intomicrosoft:mainfrom
rachana192837 wants to merge 1 commit intomicrosoft:mainfrom
Conversation
Author
|
@microsoft-github-policy-service agree |
codeCraft-Ritik
left a comment
codeCraft-Ritik
left a comment
There was a problem hiding this comment.
Great fix! This effectively addresses the CUDA OOM issue for long-form scripts.
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes #157 (CUDA OOM on long scripts).
Long-form scripts (>10 min) caused the 1.5B multi-speaker model to crash due to GPU memory limits.
Changes
How to Test
long_script_inference.py.Notes