Skip to main content
Glama
Eliovp-BV

MCP vLLM Benchmarking Tool

by Eliovp-BV

Herramienta de evaluación comparativa MCP vLLM

Esta es una prueba de concepto sobre cómo utilizar MCP para evaluar de forma interactiva vLLM.

No somos nuevos en benchmarking, lea nuestro blog:

Evaluación comparativa de vLLM

Esta es solo una exploración de posibilidades con MCP.

Uso

  1. Clonar el repositorio

  2. Agreguelo a sus servidores MCP:

{
    "mcpServers": {
        "mcp-vllm": {
            "command": "uv",
            "args": [
                "run",
                "/Path/TO/mcp-vllm-benchmarking-tool/server.py"
            ]
        }
    }
}

Entonces puedes indicar un ejemplo como este:

Do a vllm benchmark for this endpoint: http://10.0.101.39:8888 
benchmark the following model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B 
run the benchmark 3 times with each 32 num prompts, then compare the results, but ignore the first iteration as that is just a warmup.

Related MCP server: LLM API Benchmark MCP Server

Hacer:

  • Debido a algunas salidas aleatorias de vllm, es posible que se indique que encontró un JSON no válido. Aún no lo he investigado.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables benchmarking of local LLM models (performance and quality) and sharing results to a public leaderboard via MCP tools.
    8 npm
    8
    Apache 2.0
  • A
    license
    B
    quality
    A
    maintenance
    Enables building and running custom LLM benchmarks with multi-judge evaluation, supporting GUI, MCP client, and CLI usage for ranked, auditable results.
    3
    MIT