diff --git a/models/demos/llama3/lt b/models/demos/llama3/lt index 2a8071092377..c3e9c7b830bc 100644 --- a/models/demos/llama3/lt +++ b/models/demos/llama3/lt @@ -827,10 +827,14 @@ def run_entry_command(entry, screen_lock, output_entries, screen_needs_update): command_shortcuts = { "accuracy": "pytest models/demos/llama3/tests/test_llama_accuracy.py -k 'attention-performance and file'", "accuracy-acc": "pytest models/demos/llama3/tests/test_llama_accuracy.py -k 'attention-acc and file'", - "demo": "pytest models/demos/llama3/demo/demo.py -k performance-batch-1", - "demo-acc": "pytest models/demos/llama3/demo/demo.py -k accuracy-batch-1", - "demo-32": "pytest models/demos/llama3/demo/demo.py -k performance-batch-32", - "demo-long": "pytest models/demos/llama3/demo/demo.py -k performance-long", + "demo": "pytest models/demos/llama3/demo/simple_text_demo.py -k performance-batch-1", + "demo-acc": "pytest models/demos/llama3/demo/simple_text_demo.py -k accuracy-batch-1", + "demo-32": "pytest models/demos/llama3/demo/simple_text_demo.py -k performance-batch-32", + "demo-long": "pytest models/demos/llama3/demo/simple_text_demo.py -k performance-long", + "leg-demo": "pytest models/demos/llama3/demo/demo.py -k performance-batch-1", + "leg-demo-acc": "pytest models/demos/llama3/demo/demo.py -k accuracy-batch-1", + "leg-demo-32": "pytest models/demos/llama3/demo/demo.py -k performance-batch-32", + "leg-demo-long": "pytest models/demos/llama3/demo/demo.py -k performance-long", "attention": "pytest models/demos/llama3/tests/test_llama_attention.py", "attention-prefill": "pytest models/demos/llama3/tests/test_llama_attention_prefill.py", "mlp": "pytest models/demos/llama3/tests/test_llama_mlp.py",