-
Notifications
You must be signed in to change notification settings - Fork 34
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] Fix a but within FP8 E4M3 Fast Decoding #54
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
…into lei/splitk
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Outdated suggestions cannot be applied.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 primarily focuses on enhancing the functionality of the
bitblas
Python package and updating the version number. The main changes include the addition ofMatmulConfigWithSplitK
andMatmulWithSplitK
in thebitblas
module, updates to thegemv
andgemv_dequantize
modules to support more iterations, and modifications to thequantization
module for better handling of floating point numbers. The version number has also been updated from0.0.1.dev9
to0.0.1.dev12
.Version Update:
VERSION
andpython/bitblas/__init__.py
: Updated the version number from0.0.1.dev9
to0.0.1.dev12
. [1] [2]Enhancements to
bitblas
module:python/bitblas/__init__.py
: ImportedMatmulConfigWithSplitK
andMatmulWithSplitK
fromgeneral_matmul_splitk
module.Updates to
gemv
andgemv_dequantize
modules:python/bitblas/gpu/gemv.py
: Extended the acceptable range ofblock_info.iters
length to include 4.python/bitblas/gpu/gemv_dequantize.py
: Adjusted the logic inget_vectorize_factor
to handle cases where the length ofsch.get_loops(block_b)
is 4. [1] [2]Modifications to
quantization
module:python/bitblas/quantization/quantization.py
: Revised_tir_u8_to_f8_e4m3_to_f16
function and added a new function_tir_u8_to_f8_e4m3_to_f16_naive
for better handling of floating point numbers.Other Changes:
python/bitblas/wrapper/general.py
: Modified thelegalize_c
function to handle cases wheredynamic_symbolic_set
is not empty.testing/python/operators/test_general_matmul_splitk_ops.py
: Added additional calls tomatmul.forward
for testing purposes.