init

AlgoriAgent/scripts/vllm/model_config.json

@@ -0,0 +1,12 @@
+{
+    "model_type": "openai_chat",
+    "config_name": "vllm_llama2-7b-chat-hf",
+    "model_name": "meta-llama/Llama-2-7b-chat-hf",
+    "api_key": "EMPTY",
+    "client_args": {
+        "base_url": "http://localhost:8000/v1/"
+    },
+    "generate_args": {
+        "temperature": 0.5
+    }
+}

AlgoriAgent/scripts/vllm/vllm_setup.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+# pip3 install vllm
+
+model_name_or_path="meta-llama/Llama-2-7b-chat-hf"
+port=8000
+
+while getopts "m:p:" flag
+do
+    # shellcheck disable=SC2220
+    case "${flag}" in
+        m) model_name_or_path=${OPTARG};;
+        p) port=${OPTARG};;
+    esac
+done
+
+python -m vllm.entrypoints.openai.api_server --model "${model_name_or_path}" \
+  --port "${port}" --enforce-eager