Add NvTenosrRtRtx ep in example file (#1656)

- Add NvTenosrRtRtx ep in example file

Author: anujj

examples/chat_app/app.py

@@ -82,6 +82,8 @@ def get_ep_name(name):
         return "cuda"
     elif "dml" in new_name:
         return "dml"
+    elif "nvtensorrtrtx" in new_name:
+        return "NvTensorRtRtx"
     raise ValueError(f"{new_name} is not recognized.")
 
 

examples/chat_app/interface/hddr_llm_onnx_interface.py

@@ -1,4 +1,5 @@
 import gc
+import logging
 import os
 import sys
 import onnxruntime_genai as og

examples/python/model-generate.py

@@ -79,7 +79,7 @@ def main(args):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(argument_default=argparse.SUPPRESS, description="End-to-end token generation loop example for gen-ai")
     parser.add_argument('-m', '--model_path', type=str, required=True, help='Onnx model folder path (must contain genai_config.json and model.onnx)')
-    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
+    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "NvTensorRtRtx", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
     parser.add_argument('-pr', '--prompts', nargs='*', required=False, help='Input prompts to generate tokens from. Provide this parameter multiple times to batch multiple prompts')
     parser.add_argument('-i', '--min_length', type=int, default=25, help='Min number of tokens to generate including the prompt')
     parser.add_argument('-l', '--max_length', type=int, default=50, help='Max number of tokens to generate including the prompt')

examples/python/model-qa.py

@@ -198,7 +198,7 @@ def main(args):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(argument_default=argparse.SUPPRESS, description="End-to-end AI Question/Answer example for gen-ai")
     parser.add_argument('-m', '--model_path', type=str, required=True, help='Onnx model folder path (must contain genai_config.json and model.onnx)')
-    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
+    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "NvTensorRtRtx", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
     parser.add_argument('-i', '--min_length', type=int, help='Min number of tokens to generate including the prompt')
     parser.add_argument('-l', '--max_length', type=int, help='Max number of tokens to generate including the prompt')
     parser.add_argument('-ds', '--do_sample', action='store_true', help='Do random sampling. When false, greedy or beam search are used to generate the output. Defaults to false')

examples/python/phi3-qa.py

@@ -85,7 +85,7 @@ def main(args):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(argument_default=argparse.SUPPRESS, description="End-to-end AI Question/Answer example for gen-ai")
     parser.add_argument('-m', '--model_path', type=str, required=True, help='Onnx model folder path (must contain genai_config.json and model.onnx)')
-    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
+    parser.add_argument('-e', '--execution_provider', type=str, required=False, default='follow_config', choices=["cpu", "cuda", "dml", "NvTensorRtRtx", "follow_config"], help="Execution provider to run the ONNX Runtime session with. Defaults to follow_config that uses the execution provider listed in the genai_config.json instead.")
     parser.add_argument('-i', '--min_length', type=int, help='Min number of tokens to generate including the prompt')
     parser.add_argument('-l', '--max_length', type=int, help='Max number of tokens to generate including the prompt')
     parser.add_argument('-ds', '--do_sample', action='store_true', default=False, help='Do random sampling. When false, greedy or beam search are used to generate the output. Defaults to false')