You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
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
@PenghuiCheng please check!
Traceback (most recent call last):
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/quantization.py", line 234, in fit
strategy.traverse()
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/strategy/auto.py", line 140, in traverse
super().traverse()
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/strategy/strategy.py", line 482, in traverse
self._setup_pre_tuning_algo_scheduler()
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/strategy/strategy.py", line 360, in _setup_pre_tuning_algo_scheduler
self.model = self._pre_tuning_algo_scheduler("pre_quantization")
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/algorithm/algorithm.py", line 127, in call
self._q_model = algo(self._origin_model, self._q_model, self._adaptor, self._dataloader, self._calib_iter)
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/algorithm/smooth_quant.py", line 89, in call
q_model = adaptor.smooth_quant(
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/adaptor/pytorch.py", line 1796, in smooth_quant
model._model = self.sq.transform(
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/adaptor/torch_utils/smooth_quant.py", line 1286, in transform
out_pre_sq = model_forward_per_sample(self.model, example_inputs, self.device)
File "/home/sdp/miniconda3/envs/pt-ipex-2.1.0+cpu-3.10-spr/lib/python3.10/site-packages/neural_compressor/adaptor/torch_utils/smooth_quant.py", line 110, in model_forward_per_sample
output = forward_wrapper(model, sample[0], device)
KeyError: 0
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.
PenghuiCheng
force-pushed
the
penghuic/Fixed_t5_model_issue
branch
from
Type of Change
bug fix
No API changed
Description
Fixed quantization failure when T5 base model be quantized with IPEX smoothquant.
Expected Behavior & Potential Risk
Quantize successfully
How has this PR been tested?
Local tested