Skip to content

Commit

Permalink
fix ut issue
Browse files Browse the repository at this point in the history
Signed-off-by: Mengni Wang <[email protected]>
  • Loading branch information
mengniwang95 committed Jun 27, 2024
1 parent c011617 commit ecbb392
Showing 1 changed file with 3 additions and 0 deletions.
3 changes: 3 additions & 0 deletions onnx_neural_compressor/quantization/matmul_4bits_quantizer.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
from typing import List, Union # isort: skip

import onnx
import onnxruntime as ort

from onnx_neural_compressor.quantization import matmul_nbits_quantizer

Expand All @@ -34,6 +35,7 @@ def __init__(
nodes_to_exclude=None,
algo_config: matmul_nbits_quantizer.WeightOnlyQuantConfig = None,
providers: List[str] = ["CPUExecutionProvider"],
optimization_level: ort.GraphOptimizationLevel = ort.GraphOptimizationLevel.ORT_ENABLE_BASIC,
):
super().__init__(
model=model,
Expand All @@ -44,4 +46,5 @@ def __init__(
algo_config=algo_config,
n_bits=4,
providers=providers,
optimization_level=optimization_level,
)

0 comments on commit ecbb392

Please sign in to comment.