feat: initial commit with vLLM production stack and benchmark tools

This commit is contained in:
jrodriiguezg
2026-09-09 18:22:40 +02:00
commit 20ae3cfb48
10 changed files with 331 additions and 0 deletions
+19
View File
@@ -0,0 +1,19 @@
global:
scrape_interval: 2s # Intervalo corto para capturar datos de latencia y saturación
evaluation_interval: 2s
scrape_configs:
- job_name: 'vllm'
metrics_path: '/metrics'
static_configs:
- targets: ['vllm:8000']
labels:
engine: 'vllm'
model: 'qwen2.5-3b-awq'
- job_name: 'litellm'
metrics_path: '/metrics'
static_configs:
- targets: ['litellm:4000']
labels:
service: 'llm-gateway'