[Dev][TL] Enhance TL Paser to support flexible tile lang kernel implementation #222
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
Contributor
Author
|
Also fix for issue #221 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 pull request includes several changes to the
bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.pyfile, focusing on refactoring and enhancing the dequantization process. It also updates thebitblas/ops/base_scheduler.pyfile to add an assertion for function simplification and modifies test cases intesting/python/operators/test_general_matmul_tilelang_scheduler.pyto include new dequantization scenarios.Enhancements to Dequantization Process:
apply_configmethod to streamline the configuration process and removed redundant methods for different scaling and zero modes. (bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.py, [1] [2]_normal_dequantmethod for handling different dequantization scenarios based on scaling and zero modes. (bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.py, bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.pyR367-R488)bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.py, bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.pyR222-R226)Code Quality Improvements:
Simplifymethod returns a single function and added an assertion to enforce this. (bitblas/ops/base_scheduler.py, bitblas/ops/base_scheduler.pyL30-R32)zeros_modedefault value to a tuple format. (bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.py, bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.pyL52-R52)bitblas/ops/general_matmul/tilelang/dequantize/block_primitive_tensorcore.py, [1] [2] [3]Test Cases:
testing/python/operators/test_general_matmul_tilelang_scheduler.py, testing/python/operators/test_general_matmul_tilelang_scheduler.pyR37-R92)Submodule Update:
tvmsubmodule to a new commit. (3rdparty/tvm, 3rdparty/tvmL1-R1)