Chapter 5. Viewing AI Inference Server metrics

Procedure

1. Launch the AI Inference Server server and load your model as shown in the following example. The command also exposes the OpenAI-compatible API.

   $ vllm serve unsloth/Llama-3.2-1B-Instruct

2. Query the /metrics endpoint of the OpenAI-compatible API to get the latest metrics from the server:

   $ curl http://0.0.0.0:8000/metrics

   Example output

   # HELP vllm:iteration_tokens_total Histogram of number of tokens per engine_step.
   # TYPE vllm:iteration_tokens_total histogram
   vllm:iteration_tokens_total_sum{model_name="unsloth/Llama-3.2-1B-Instruct"} 0.0
   vllm:iteration_tokens_total_bucket{le="1.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="8.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="16.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="32.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="64.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="128.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="256.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   vllm:iteration_tokens_total_bucket{le="512.0",model_name="unsloth/Llama-3.2-1B-Instruct"} 3.0
   #...