Use optimized library if op available #324
Closed
Conversation
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D49240517 |
|
This pull request was exported from Phabricator. Differential Revision: D49240517 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D49240517 |
Summary: Some models (transformer models) has ops like bmm and optimized library providers a better performance than portable. With optimized: https://www.internalfb.com/intern/aibench/details/125435623160736 (750 ms per iteration) With portable: https://www.internalfb.com/intern/aibench/details/521699054450309 (1200 ms per iteration) Differential Revision: D49240517
|
This pull request was exported from Phabricator. Differential Revision: D49240517 |
|
This pull request has been merged in 192da36. |
Gasoonjia
pushed a commit
that referenced
this pull request
Jul 30, 2024
* refactor quantizer entry point quantize_model to be table driven, and scalable * add tokenizer arg consistently * code beautification
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Outdated suggestions cannot be applied.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.
Summary:
Some models (transformer models) has ops like bmm and optimized library providers a better performance than portable.
With optimized: https://www.internalfb.com/intern/aibench/details/125435623160736 (750 ms per iteration)
With portable: https://www.internalfb.com/intern/aibench/details/521699054450309 (1200 ms per iteration)
Differential Revision: D49240517