Fix support const as input to linear layers in pytorch #1080
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
elad-c
reviewed
May 21, 2024
| @@ -56,7 +56,7 @@ def __init__(self, unit_test, func, const, input_reverse_order=False): | |||
| def get_tpc(self): | |||
| tp = generate_test_tp_model({'weights_n_bits': 32, | |||
| 'activation_n_bits': 32, | |||
| 'enable_weights_quantization': False, | |||
| 'enable_weights_quantization': True, | |||
There was a problem hiding this comment.
maybe test with AND without weights quantization?
|
@lapid92 |
ofirgo
requested changes
May 21, 2024
| @@ -239,7 +239,9 @@ def insert_positional_weights_to_input_list(self, input_tensors: List) -> List: | |||
| for pos, weight in sorted((pos, weight) for pos, weight in self.weights.items() | |||
| if isinstance(pos, int)): | |||
| assert pos <= len(input_tensors), 'Positional weight index mismatch' | |||
| input_tensors.insert(pos, weight) | |||
| # Insert only positional weights that are not subject to quantization. | |||
| @@ -239,7 +239,9 @@ def insert_positional_weights_to_input_list(self, input_tensors: List) -> List: | |||
| for pos, weight in sorted((pos, weight) for pos, weight in self.weights.items() | |||
| if isinstance(pos, int)): | |||
| assert pos <= len(input_tensors), 'Positional weight index mismatch' | |||
There was a problem hiding this comment.
change this to if with a "critical" logger message
ofirgo
approved these changes
May 22, 2024
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Outdated suggestions cannot be applied.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.
Pull Request Description:
The issue is that positional weights are only inserted as inputs to the node if the positional weights of the node are being quantized, and in any case where the node weights are not being quantized.
The PR addresses the scenario where the node weights are being quantized and the positional weights are not quantized.
Checklist before requesting a review: