Optimization in Q8_0 loading#74
Merged
mikepapadim merged 5 commits intobeehive-lab:mainfrom Nov 28, 2025
Merged
Conversation
… FP32 conversion logic.
… for consistency
Member
|
/rerun all |
Contributor
|
🚀 Workflow rerun started Mode: |
Contributor
|
✅ Workflow rerun success |
Member
|
/rerun help |
Contributor
🔄 Rerun Workflow Commands
Note: Only completed workflows can be rerun. In-progress workflows are skipped. |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR improves performance of loading for q8_0 models by parallelizing tensor copy from MemorySegment to TornadoNativeArray types. Also it avoids one round of conversion.
Llama3.2-1B-Q8_0loading avg times on rog laptop: