Init

api_writer/vllm_api.py

@@ -19,7 +19,7 @@ def http_bot(prompt):
     prompt = eval_chat_template.format(SYSTEM=system_context, INPUT=prompt)
     pload = deepcopy(sampling_params)
     pload['prompt']=prompt
-    response = requests.post('http://localhost:8000/v1/completions',
+    response = requests.post('http://localhost:8001/v1/completions',
                              headers=headers,
                              json=pload,
                              stream=True)