replacing rccl_float8 with hip_fp8 and address compatibility issue #1546
+56
−5
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Outdated suggestions cannot be applied.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.
Details
Work item: _ [LWPCOMMLIBS-576]
What were the changes?
move to HIP FP8 header file
Why were the changes made?
RCCL needs to switch over to HIP FP8 header file which has become available in recent ROCm releases.
How was the outcome achieved?
RCCL-UT and rccl-tests have been tested and passed with datatype=FP8.
Additional Documentation:
What else should the reviewer know?
For gfx942, we need to support FP8_FNUZ, as the OCP type is currently unsupported. Additionally, we should retain the current RCCL internal header file to ensure compatibility with older ROCm releases that lack the HIP FP8 header.
Approval Checklist
Do not approve until these items are satisfied.