Fix nncf quantization for decoder models #727
Merged
Conversation
This file contains 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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
echarlaix
commented
May 24, 2024
| @@ -419,7 +420,7 @@ def prepare_inputs( | |||
| shape[2] = 0 | |||
| else: | |||
| shape[1] = 0 | |||
| inputs[input_name] = Tensor(model_inputs.get_element_type(), shape.get_shape()) | |||
| inputs[input_name] = np.empty([dim.get_length() for dim in shape], dtype=dtype) | |||
There was a problem hiding this comment.
Looks like instances of openvino.runtime.Tensor cannot be pickled which is needed for the fix added in #632 for the InferRequestWrapper
AlexKoff88
reviewed
May 24, 2024
nikita-savelyevv
approved these changes
May 24, 2024
AlexKoff88
approved these changes
May 24, 2024
faaany
pushed a commit
to faaany/optimum-intel
that referenced
this pull request
May 26, 2024
* Fix nncf quantization for decoder models * add test * update op quant op * remove deprecated warning * update expected quantized * enable stateful * style
Merged
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Outdated suggestions cannot be applied.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.
Added a fix to be able to quantize instances of
OVModelForCausalLMusing the quantizercc @nikita-savelyevv