[Dev] Rename signature FineGrain in Kernel with MMA as MFMA implementation will be introduced for rocm#289
Merged
LeiWang1999 merged 4 commits intomicrosoft:mainfrom Feb 2, 2025
LeiWang1999:separate_mma
Merged
[Dev] Rename signature FineGrain in Kernel with MMA as MFMA implementation will be introduced for rocm#289LeiWang1999 merged 4 commits intomicrosoft:mainfrom LeiWang1999:separate_mma
FineGrain in Kernel with MMA as MFMA implementation will be introduced for rocm#289LeiWang1999 merged 4 commits intomicrosoft:mainfrom
LeiWang1999:separate_mma
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request includes significant changes to the matrix multiplication and dequantization scheduling code in the
bitblaslibrary. The primary changes involve replacing the existing TensorCore-based schedulers with new Tile Library and MMA-based schedulers. Additionally, several files have been renamed to reflect these changes.Scheduler Updates:
MatmulBlockScheduler,MatmulFineGrainScheduler, andMatmulWeightPropagationSchedulerwithMatmulTileLibraryScheduler,MatmulMMAScheduler, andMatmulMMAWeightPropagationSchedulerrespectively inbitblas/ops/general_matmul/tilelang/dense/__init__.py.MatmulDequantizeBlockScheduler,MatmulDequantizeFineGrainedScheduler, andMatmulDequantizeWeightPropagationSchedulertoMatmulDequantizeTileLibraryScheduler,MatmulDequantizeMMAScheduler, andMatmulDequantizeMMAWeightPropagationSchedulerrespectively inbitblas/ops/general_matmul/tilelang/dequantize/__init__.py.Function and Class Updates:
is_int4_dtypefunction to use the new MMA-based schedulers inbitblas/ops/general_matmul/tilelang/dense/__init__.py. [1] [2] [3]MatmulSchedulerclass to use the new schedulers inbitblas/ops/general_matmul/tilelang/dense/matmul.py.bitblas/ops/general_matmul/tilelang/dequantize/matmul_dequantize_mma.py. [1] [2] [3]File Renaming:
matmul_dequantize_tensorcore_finegrained.pytomatmul_dequantize_mma.pyand updated its imports and class names accordingly. [1] [2]matmul_dequantize_tensorcore_weight_transform.pytomatmul_dequantize_mma_weight_transform.pyand updated its imports and class names accordingly. [1] [2]matmul_dequantize_tensorcore.pytomatmul_dequantize_tile.pyand updated its imports and class names accordingly. [1] [2] [3]Test Updates:
testing/python/operators/test_general_matmul_tilelang_impl.pyandtesting/python/operators/test_general_matmul_tilelang_kernel.py. [1] [2]