update vllm0.5.0

examples/openai_example_batch.jsonl

+{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}
+{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Hello world!"}],"max_tokens": 1000}}

examples/production_monitoring/prometheus.yaml

+# prometheus.yaml
+global:
+  scrape_interval: 5s
+  evaluation_interval: 30s
+
+scrape_configs:
+  - job_name: vllm
+    static_configs:
+      - targets:
+          - 'host.docker.internal:8000'