fix low_gpu_mem_usage=True

Signed-off-by: Kaihui-intel <[email protected]>
intel · Jul 26, 2024 · 1f7f696 · 1f7f696
1 parent 6e1b1da
commit 1f7f696
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/neural_compressor/torch/quantization/config.py b/neural_compressor/torch/quantization/config.py
@@ -905,7 +905,7 @@ def __init__(
         enable_minmax_tuning: bool = True,
         lr: float = None,
         minmax_lr: float = None,
-        low_gpu_mem_usage: bool = True,
+        low_gpu_mem_usage: bool = False,
         iters: int = 200,
         seqlen: int = 2048,
         nsamples: int = 128,
@@ -938,7 +938,7 @@ def __init__(
             enable_minmax_tuning (bool): Whether to enable min-max tuning (default is True).
             lr (float): The learning rate (default is 0.005).
             minmax_lr (float): The learning rate for min-max tuning (default is None).
-            low_gpu_mem_usage (bool): Whether to use low GPU memory (default is True).
+            low_gpu_mem_usage (bool): Whether to use low GPU memory (default is False).
             iters (int): Number of iterations (default is 200).
             seqlen (int): Length of the sequence.
             nsamples (int): Number of samples (default is 512).