Repository navigation
Support the FP6 dtypes added in onnx 1.23 - #80
Merged
Merged
Conversation
onnx 1.23 adds FLOAT6E2M3 and FLOAT6E3M2, packed at 6 bits per element. Add them to ITEMBITS so the converter sizes them correctly and the dtype coverage test passes again on the wheel builds, which install the latest onnx rather than the locked one.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
onnx 1.23 adds
FLOAT6E2M3andFLOAT6E3M2, whichmake_tensorpacks at 6 bits per element. They were missing fromITEMBITS, sotest_itembits_covers_every_onnx_dtypefails on everybuild_wheelsjob: cibuildwheel installs the latest onnx (1.23.2), while Checks uses the locked 1.22.0 and stays green.Adds both dtypes to
ITEMBITSand to the test's sub-byte width table. Unit tests pass with onnx 1.22.0 and 1.23.2.