Refactor input normalization by replaying inputs for consistent preprocessing #1094
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: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
for more information, see https://pre-commit.ci
…nto fix-attn-mask
wenhuach21
reviewed
Dec 4, 2025
Signed-off-by: yiliu30 <yi4.liu@intel.com>
wenhuach21
reviewed
Dec 4, 2025
|
|
||
| def _preprocess_block_inputs(self, inputs, first_input_name="input_ids"): | ||
| input_ids, input_others = self._split_inputs(inputs, first_input_name) | ||
| clear_memory(device_list=self.device_list) |
Contributor
There was a problem hiding this comment.
I don''t know why clear_memory is needed here. @n1ck-guo do you know?
wenhuach21
reviewed
Dec 4, 2025
| input_ids, input_others = normalize_input(inputs) | ||
| self.normalize_decoding_layer_inputs_(inputs) | ||
| block_inputs = self.inputs[self.quant_block_list[0][0]] | ||
| decoding_layer_first_input_name = "hidden_states" |
Contributor
There was a problem hiding this comment.
does the origin code have such assumption? Is there any case that the first_input_name is not hidden_states
Contributor
Author
There was a problem hiding this comment.
The origin code replaces the hidden_states with input_ids.
Signed-off-by: yiliu30 <yi4.liu@intel.com>
wenhuach21
approved these changes
Dec 5, 2025
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Outdated suggestions cannot be applied.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.
No description provided.