Change the name to vLLM (#150)

examples/api_client.py

@@ -1,4 +1,4 @@
-"""Example Python client for cacheflow.entrypoints.api_server"""
+"""Example Python client for vllm.entrypoints.api_server"""
 
 import argparse
 import json

examples/gradio_webserver.py

@@ -6,7 +6,7 @@ import requests
 
 
 def http_bot(prompt):
-    headers = {"User-Agent": "Cacheflow Client"}
+    headers = {"User-Agent": "vLLM Client"}
     pload = {
         "prompt": prompt,
         "stream": True,
@@ -24,7 +24,7 @@ def http_bot(prompt):
 def build_demo():
     with gr.Blocks() as demo:
         gr.Markdown(
-            "# Cacheflow text completion demo\n"
+            "# vLLM text completion demo\n"
         )
         inputbox = gr.Textbox(label="Input", placeholder="Enter text and press ENTER")
         outputbox = gr.Textbox(label="Output", placeholder="Generated result from the model")

examples/llm_engine_example.py

@@ -1,6 +1,6 @@
 import argparse
 
-from cacheflow import EngineArgs, LLMEngine, SamplingParams
+from vllm import EngineArgs, LLMEngine, SamplingParams
 
 
 def main(args: argparse.Namespace):

examples/offline_inference.py

@@ -1,4 +1,4 @@
-from cacheflow import LLM, SamplingParams
+from vllm import LLM, SamplingParams
 
 
 # Sample prompts.

examples/openai_client.py

@@ -1,6 +1,6 @@
 import openai
 
-# Modify OpenAI's API key and API base to use CacheFlow's API server.
+# Modify OpenAI's API key and API base to use vLLM's API server.
 openai.api_key = "EMPTY"
 openai.api_base = "http://localhost:8000/v1"
 model = "facebook/opt-125m"