[tritonbench] Benchmark int4 gemm implementations #2261
Closed
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
Summary: Focusing on llama2-70b inference, this compares tinygemm (_weight_int4pack_mm) to a Triton implementation. Note that these are not numerically equivalent now, as the Triton implementation does not apply scale and zero point. TODO! Test Plan: ``` pytorch run_benchmark.py triton --op int4_gemm ```
bertmaher
temporarily deployed
to
docker-s3-upload
GitHub Actions
Inactive
|
@bertmaher has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
bertmaher
temporarily deployed
to
docker-s3-upload
GitHub Actions
Inactive
|
@bertmaher merged this pull request in 43621bc. |
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Outdated suggestions cannot be applied.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.
Summary: Focusing on llama2-70b inference, this compares tinygemm (_weight_int4pack_mm) to a Triton implementation.
Note that these are not numerically equivalent now, as the Triton implementation does not apply scale and zero point. TODO!
Test Plan: