We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent f9a468a commit 90f004bCopy full SHA for 90f004b
python/llm/example/CPU/Deepspeed-AutoTP/deepspeed_autotp.py
@@ -50,7 +50,6 @@
50
import intel_extension_for_pytorch as ipex
51
import time
52
import argparse
53
-from benchmark_util import BenchmarkWrapper
54
55
if __name__ == '__main__':
56
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for Llama2 model')
@@ -94,7 +93,6 @@
94
93
model = model.to(f'cpu:{local_rank}')
95
96
print(model)
97
- model = BenchmarkWrapper(model, do_print=True)
98
99
# Load tokenizer
100
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
0 commit comments