New performance testing tools

Author: Menglths

test/common/llmperf/utils/llm_client.py

@@ -14,7 +14,7 @@ def llm_request(
         """Make a single completion request to a LLM API
 
         Returns:
-            Metrics about the performance charateristics of the request.
+            Metrics about the performance characteristics of the request.
             The text generated by the request to the LLM API.
             The request_config used to make the request. This is mainly for logging purposes.
 

test/common/llmperf/utils/utils.py

@@ -145,7 +145,7 @@ def flatten_dict(d, parent_key="", sep="_"):
 def reset_prefill_cache(env, server_url):
     """
     prefix cache / HBM
-    Parm：
+    Param：
         env
         server_url
     """