Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] fused mixtral wint4 #9013

Merged
merged 2 commits into from
Aug 27, 2024

Conversation

penPenf28
Copy link
Contributor

PR types

New features

PR changes

Models

Description

支持mixtral模型wint4

Copy link

paddle-bot bot commented Aug 26, 2024

Thanks for your contribution!

Copy link

codecov bot commented Aug 26, 2024

Codecov Report

Attention: Patch coverage is 0% with 3 lines in your changes missing coverage. Please review.

Project coverage is 54.12%. Comparing base (154928a) to head (2f3c818).
Report is 229 commits behind head on develop.

Files with missing lines Patch % Lines
...erimental/transformers/fused_transformer_layers.py 0.00% 3 Missing ⚠️
Additional details and impacted files
@@             Coverage Diff             @@
##           develop    #9013      +/-   ##
===========================================
+ Coverage    54.06%   54.12%   +0.05%     
===========================================
  Files          650      650              
  Lines       103883   103874       -9     
===========================================
+ Hits         56164    56221      +57     
+ Misses       47719    47653      -66     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.


🚨 Try these New Features:

ffn1_quanted_weight_list_i.reshape([self.transformer_block.config.embed_dim, -1])
ffn1_quanted_weight_list_i.reshape(
[self.transformer_block.embed_dim, self.transformer_block.dim_feedforward * 2]
if self.transformer_block.config.quant_type == "weight_only_int8"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if self.transformer_block.config.quant_type == "weight_only_int8"
if self.quant_type == "weight_only_int8"

这样就可以吧

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

ffn2_quanted_weight_list_i.reshape([-1, self.transformer_block.config.embed_dim])
ffn2_quanted_weight_list_i.reshape(
[self.transformer_block.dim_feedforward, self.transformer_block.embed_dim]
if self.transformer_block.config.quant_type == "weight_only_int8"
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

同上

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

Copy link
Contributor

@DesmonDay DesmonDay left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@wawltor wawltor merged commit f6fc7ff into PaddlePaddle:develop Aug 27, 2024
10 of 12 checks passed
lixcli pushed a commit to lixcli/PaddleNLP that referenced this pull request Aug 28, 2024
* [Feature] fused mixtral wint4

* [Refactor] refine code
lixcli pushed a commit to lixcli/PaddleNLP that referenced this pull request Aug 28, 2024
* [Feature] fused mixtral wint4

* [Refactor] refine code
lixcli pushed a commit to lixcli/PaddleNLP that referenced this pull request Aug 28, 2024
* [Feature] fused mixtral wint4

* [Refactor] refine code
Mangodadada pushed a commit to Mangodadada/PaddleNLP that referenced this pull request Sep 10, 2024
* [Feature] fused mixtral wint4

* [Refactor] refine code
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants