Skip to content

[Operators] preliminary symmetric weight quantization#298

Merged
yaoyaoding merged 10 commits intohidet-org:mainfrom
Aalanli:linear-layer-quantization
Jul 4, 2023
Merged

[Operators] preliminary symmetric weight quantization#298
yaoyaoding merged 10 commits intohidet-org:mainfrom
Aalanli:linear-layer-quantization

Conversation

@Aalanli
Copy link
Copy Markdown
Contributor

@Aalanli Aalanli commented Jun 30, 2023

  • Added preliminary symmetric weight quantization in tasks
  • Changed Operator._run to Operator.symbolic_run, such that construction of the operator does not automatically run imperative_run, but symbolic_run. This is so that constant folding does not happen with barrier op, and leads to the intended behaviour with quantization layers. This should be fine to do since all imperative calls calls op.get_output(...), anyways, which calls imperative_run

@Aalanli Aalanli requested a review from yaoyaoding June 30, 2023 19:27
Copy link
Copy Markdown
Member

@yaoyaoding yaoyaoding left a comment

Choose a reason for hiding this comment

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

Thanks @Aalanli !

I left some comments, and made some update directly on this PR.

I refactored a little bit on the run, symbolic_run and imperative_run.

Copy link
Copy Markdown
Contributor Author

@Aalanli Aalanli left a comment

Choose a reason for hiding this comment

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

Thanks for the changes, makes sense.

@yaoyaoding
Copy link
Copy Markdown
Member

Thanks @Aalanli !

@yaoyaoding yaoyaoding merged commit f937ad2 into hidet-org:main Jul 4, 2023
@Aalanli Aalanli deleted the linear-layer-quantization branch September 27, 2023 18:09
vadiklyutiy pushed a commit that referenced this pull request Dec 19, 2024
…. ) (#294)

[Ir][Primitives] add vectorized conversion instructions
[Ir][CuTe] add reduce primitives in cute (#295)
[Ir][CuTe] add mma primitives (#296)
[Ir][CuTe] add other primitives in cute (#297)
[Transforms][CuTe] add instruction selection pass (#298)
[Transforms][CuTe] add resolve bank conflict pass (#299)
[Transforms][CuTe] add resolve auto keywords pass (#300)
[Transforms][CuTe] add shared memory allocation pass (#301)
[Transforms][CuTe] add vectorize elementwise operation pass (#302)
[Transforms][CuTe] add analysis pass (#303)
[Transforms][CuTe] add canonicalization pass (#304)
[Transforms][CuTe] add deadcode elimination pass (#305)
[Transforms][CuTe] refactor cute lowering pass (#306)
[Graph][Ops] matmul cute (#307)
[Ir] cute miscs (#308)
[Tests] cute tests (#309)
[Chore] fix ci (#313)
---------

Co-authored-by: xiaocenxiaocen <xiao.zhang@centml.ai>
vadiklyutiy pushed a commit that referenced this pull request Dec 20, 2024
…. ) (#294)

[Ir][Primitives] add vectorized conversion instructions
[Ir][CuTe] add reduce primitives in cute (#295)
[Ir][CuTe] add mma primitives (#296)
[Ir][CuTe] add other primitives in cute (#297)
[Transforms][CuTe] add instruction selection pass (#298)
[Transforms][CuTe] add resolve bank conflict pass (#299)
[Transforms][CuTe] add resolve auto keywords pass (#300)
[Transforms][CuTe] add shared memory allocation pass (#301)
[Transforms][CuTe] add vectorize elementwise operation pass (#302)
[Transforms][CuTe] add analysis pass (#303)
[Transforms][CuTe] add canonicalization pass (#304)
[Transforms][CuTe] add deadcode elimination pass (#305)
[Transforms][CuTe] refactor cute lowering pass (#306)
[Graph][Ops] matmul cute (#307)
[Ir] cute miscs (#308)
[Tests] cute tests (#309)
[Chore] fix ci (#313)
---------

Co-authored-by: xiaocenxiaocen <xiao.zhang@centml.ai>
vadiklyutiy pushed a commit that referenced this pull request Dec 26, 2024
…. ) (#294)

[Ir][Primitives] add vectorized conversion instructions
[Ir][CuTe] add reduce primitives in cute (#295)
[Ir][CuTe] add mma primitives (#296)
[Ir][CuTe] add other primitives in cute (#297)
[Transforms][CuTe] add instruction selection pass (#298)
[Transforms][CuTe] add resolve bank conflict pass (#299)
[Transforms][CuTe] add resolve auto keywords pass (#300)
[Transforms][CuTe] add shared memory allocation pass (#301)
[Transforms][CuTe] add vectorize elementwise operation pass (#302)
[Transforms][CuTe] add analysis pass (#303)
[Transforms][CuTe] add canonicalization pass (#304)
[Transforms][CuTe] add deadcode elimination pass (#305)
[Transforms][CuTe] refactor cute lowering pass (#306)
[Graph][Ops] matmul cute (#307)
[Ir] cute miscs (#308)
[Tests] cute tests (#309)
[Chore] fix ci (#313)
---------

Co-authored-by: xiaocenxiaocen <xiao.zhang@centml.ai>
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.

2 participants