Rename servers and change port numbers to reduce confusion (#149)

examples/api_client.py

@@ -1,3 +1,5 @@
+"""Example Python client for cacheflow.entrypoints.api_server"""
+
 import argparse
 import json
 from typing import Iterable, List
@@ -45,7 +47,7 @@ def get_response(response: requests.Response) -> List[str]:
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--host", type=str, default="localhost")
-    parser.add_argument("--port", type=int, default=8001)
+    parser.add_argument("--port", type=int, default=8000)
     parser.add_argument("--n", type=int, default=4)
     parser.add_argument("--prompt", type=str, default="San Francisco is a")
     parser.add_argument("--stream", action="store_true")

examples/gradio_webserver.py

@@ -9,6 +9,7 @@ def http_bot(prompt):
     headers = {"User-Agent": "Cacheflow Client"}
     pload = {
         "prompt": prompt,
+        "stream": True,
         "max_tokens": 128,
     }
     response = requests.post(args.model_url, headers=headers, json=pload, stream=True)
@@ -34,8 +35,8 @@ def build_demo():
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--host", type=str, default="localhost")
-    parser.add_argument("--port", type=int, default=8002)
-    parser.add_argument("--model-url", type=str, default="http://localhost:8001/generate")
+    parser.add_argument("--port", type=int, default=8001)
+    parser.add_argument("--model-url", type=str, default="http://localhost:8000/generate")
     args = parser.parse_args()
 
     demo = build_demo()

examples/llmserver_example.py

@@ -1,12 +1,12 @@
 import argparse
 
-from cacheflow import ServerArgs, LLMServer, SamplingParams
+from cacheflow import ServerArgs, LLMEngine, SamplingParams
 
 
 def main(args: argparse.Namespace):
     # Parse the CLI argument and initialize the server.
     server_args = ServerArgs.from_cli_args(args)
-    server = LLMServer.from_server_args(server_args)
+    server = LLMEngine.from_server_args(server_args)
 
     # Test the following prompts.
     test_prompts = [
@@ -38,7 +38,8 @@ def main(args: argparse.Namespace):
 
 
 if __name__ == '__main__':
-    parser = argparse.ArgumentParser(description='Simple CacheFlow server.')
+    parser = argparse.ArgumentParser(
+        description='Demo on using the LLMEngine class synchronously')
     parser = ServerArgs.add_cli_args(parser)
     args = parser.parse_args()
     main(args)