Fix ONNXRT diagnosis bug #1061
Merged
Fix ONNXRT diagnosis bug #1061
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
Signed-off-by: yuwenzho <[email protected]>
Signed-off-by: yuwenzho <[email protected]>
Signed-off-by: yuwenzho <[email protected]>
Signed-off-by: yuwenzho <[email protected]>
|
@bmyrcha Hi, I tested hf_albert-base-v2, hf_gpt2, hf_bart-large with diagnosis=True locally. Please help review. Thanks! |
mengniwang95
approved these changes
Jul 7, 2023
chensuyue
approved these changes
Jul 8, 2023
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Outdated suggestions cannot be applied.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.
Type of Change
bug fix
API not change
Description
Bug description:
ONNXRT GPT2 static quantization with diagnosis=True failed with error "missing scale for tensor .."
Optimized Solution:
Get scale and zero point tensor recursivly.
Check name of dump tensor is not empty.
Remove the node if it does not serve as the input or output of any other nodes.
Expected Behavior & Potential Risk
tensors can be inspected correctly for ONNXRT GPT2 static quantization with diagnosis=True
How has this PR been tested?
ONNXRT GPT2 static quantization with diagnosis=True
Dependency Change?
No