Fix bug in fp8_split_embedding_codegen_forward_kernel dispatch #2009
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Outdated suggestions cannot be applied.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:
For the case of loading FP8 tables with 128B * 8 < dimension <= 128B * 16, the numbers for (MinNum128BRows, MaxNum128BRows) should be (8, 16) and not (4, 8 ). Because of this bug, FP8 tables with dimension in that range don't get properly loaded upon codegen_forward. I wrote a little test to show this deterministically. I will remove the test before land if it is too specific.
Differential Revision: D49139649