MCP vLLM Benchmarking Tool
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
Clonar el repositorio
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: metrillm-mcp
Hacer:
Debido a algunas salidas aleatorias de vllm, es posible que se indique que encontró un JSON no válido. Aún no lo he investigado.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables benchmarking of Large Language Model APIs by measuring performance metrics such as generation throughput, prompt throughput, and Time To First Token (TTFT) with configurable concurrency levels and parameters.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables benchmarking of local LLM models (performance and quality) and sharing results to a public leaderboard via MCP tools.9 npm8Apache 2.0
- AlicenseAqualityBmaintenanceEnables building and running custom LLM benchmarks with multi-judge evaluation, supporting GUI, MCP client, and CLI usage for ranked, auditable results.8MIT
- AlicenseNot gradedqualityBmaintenanceVendor-neutral local LLM inference benchmark and hardware-config advisor for mlx and llama.cpp. Exposes an MCP tool that measures real tokens/second on your own hardware.7 npmApache 2.0