Skip to content

Commit be25725

Browse files
committed
Add num_of_instance for examples benchmark
Signed-off-by: Cheng, Penghui <[email protected]>
1 parent e94f097 commit be25725

File tree

1 file changed

+1
-1
lines changed
  • examples/pytorch/nlp/huggingface_models/language-modeling/quantization/ptq_static/fx

1 file changed

+1
-1
lines changed

examples/pytorch/nlp/huggingface_models/language-modeling/quantization/ptq_static/fx/run_clm.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -577,7 +577,7 @@ def eval_func_for_nc(model_tuned):
577577
if model_args.benchmark:
578578
from neural_compressor.config import BenchmarkConfig
579579
from neural_compressor import benchmark
580-
b_conf = BenchmarkConfig(warmup=5, iteration=100, cores_per_instance=4)
580+
b_conf = BenchmarkConfig(warmup=5, iteration=100, cores_per_instance=4, num_of_instance=1)
581581
benchmark.fit(new_model, b_conf, b_dataloader=trainer.get_eval_dataloader())
582582
else:
583583
eval_func_for_nc(new_model)

0 commit comments

Comments
 (0)