[BUG] Set Device when kernel be applied into Multiple GPUs. #155
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Outdated suggestions cannot be applied.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 improve device compatibility and streamline the weight transformation process in the
bitblasmodule. The most important changes involve modifying various functions to ensure they correctly handle the device context for GPU operations.Device Compatibility Improvements:
bitblas/module/__init__.py: Updated therepack_from_gptqmethod to accept adeviceparameter, allowing the weight transformation to be performed on the specified device.bitblas/ops/general_matmul/__init__.py: Modified thetransform_weightmethod to use the device of the input weight tensor instead of defaulting to CUDA. [1] [2]bitblas/ops/general_matmul/__init__.py: Adjusted theforwardmethod to set and use the correct CUDA stream based on the device of the input tensorA.Code Simplification:
bitblas/gpu/matmul_mma_dequantize.py: Removed obsolete condition forzeros_modeand simplified the condition forwith_scaling.