HIP Backend Improvements#218
Open
A669015 wants to merge 3 commits into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR enhances HIP support by addressing compatibility issues with modern ROCm versions and adding BF16 data type support.
Changes
cublas_wrapper.hby removing redundant HIP branches for FP16 operations where ROCm behavior now matches CUDAhipblasGemmExTesting
The compilation and install has been tested on:
All pytest tests pass successfully. Note:
test_faster_shadowexhibits intermittent failures on certain parameter sets due tograd_weightabsolute error occasionally exceeding 1e-3. This issue was already present on the master branch in the CUDA 12.8 environment and does not appear to be related to these changes.