remove htcore.hpu_inference_set_env to suit 1.20

Signed-off-by: Xin He <[email protected]>

Author: xinhe3

test/3x/torch/algorithms/fp8_quant/unit_tests/test_runtime_scale_patching.py

@@ -11,7 +11,6 @@
 from neural_compressor.torch.quantization import FP8Config, convert, prepare, finalize_calibration
 
 os.environ["PT_HPU_WEIGHT_SHARING"] = "0"
-htcore.hpu_inference_set_env()
 
 
 class TinyBlock(torch.nn.Module):