File tree Expand file tree Collapse file tree 2 files changed +1
-4
lines changed
src/compressed_tensors/quantization Expand file tree Collapse file tree 2 files changed +1
-4
lines changed Original file line number Diff line number Diff line change @@ -171,7 +171,7 @@ def from_pretrained(
171171 :param model: model to calculate quantization scheme of
172172 :return: filled out QuantizationScheme for the input model
173173 """
174- from compressed_tensors .modeling import IMPL_ATTR , KV_CACHE_ATTR
174+ from compressed_tensors .modeling import IMPL_ATTR
175175 from compressed_tensors .quantization .lifecycle .initialize import (
176176 is_attention_module ,
177177 )
Original file line number Diff line number Diff line change 1616from compressed_tensors .quantization import (
1717 DEFAULT_QUANTIZATION_FORMAT ,
1818 DEFAULT_QUANTIZATION_METHOD ,
19- QuantizationArgs ,
2019 QuantizationConfig ,
2120 QuantizationScheme ,
2221 QuantizationStatus ,
23- apply_quantization_config ,
2422)
2523from pydantic import ValidationError
26- from transformers import AutoModelForCausalLM
2724
2825
2926def test_basic_config ():
You can’t perform that action at this time.
0 commit comments