-
Notifications
You must be signed in to change notification settings - Fork 39
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
[Dev] Convert the quant compress from numpy into tvm runtime #126
Merged
Conversation
This file contains 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
…ability and maintainability
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Outdated suggestions cannot be applied.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.
By introducing the weight propagation stage3 with pr #114 , the weight transform could be bit-level when the weight is 1/2 bits. It's time for us to implement a tvm version of compress thus we can do the conversion on the unquantized weight then we can avoid the bit level permutation.
This pull request includes several important changes to the
bitblas/gpu/intrin/lop3.py
file to enhance the decoding functions, as well as a minor update to the CI workflow configuration in.github/workflows/benchmark.yml
and a submodule update in3rdparty/tvm
.Enhancements to Decoding Functions:
float16
with scaling and offset capabilities. (bitblas/gpu/intrin/lop3.py
) [1] [2] [3] [4]get_func_arguments
to streamline the passing of arguments to external functions. (bitblas/gpu/intrin/lop3.py
)offset_factor
to buffer definitions to support the new decoding functions. (bitblas/gpu/intrin/lop3.py
) [1] [2] [3] [4] [5] [6]get_func_arguments
helper for improved readability and maintainability. (bitblas/gpu/intrin/lop3.py
) [1] [2] [3] [4]CI Workflow Update:
depends-on
toneeds
in the CI workflow configuration to improve dependency management. (.github/workflows/benchmark.yml
)Submodule Update:
3rdparty/tvm
to a new version. (3rdparty/tvm
)