Add FP8 support for the ONNX backend#4072
Open
andrey-churkin wants to merge 5 commits into
Open
Conversation
daniil-lyakhov
left a comment
daniil-lyakhov
left a comment
Collaborator
There was a problem hiding this comment.
No major comments, please add some tests
Comment on lines
+367
to
+371
| if weight_dtype == onnx.TensorProto.FLOAT8E4M3FN: | ||
| np_dtype = helper.tensor_dtype_to_np_dtype(weight_dtype) | ||
| vals = onnx.numpy_helper.saturate_cast(np.asarray(quantized_weights), np_dtype).flatten() | ||
| else: | ||
| vals = quantized_weights |
Collaborator
There was a problem hiding this comment.
Two similar code blocks, maybe worth a private method?
Contributor
Author
There was a problem hiding this comment.
I've rewritten it slightly. Given that it's only two lines, I don't think introducing a separate method provides much value.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
nncf.CompressWeightsMode.FP8_E4M3mode in thenncf.compress_weights()method for the ONNX backend.nncf.QuantizationMode.FP8_E4M3andnncf.QuantizationMode.FP8_E5M2modes in thenncf.quantize()method for the ONNX backend.Reason for changes
Add support for FP8 quantization and weight compression in the ONNX backend.
Related tickets
Tests
TBD
Weight compression - success