vLLM Batch Server - Documentation Hub

🎛️ Admin Panel

Manage the server, restart workers, clear GPU memory, and monitor system health in real-time.

Open Admin Panel

Configure rate limits, GPU settings, worker parameters, and more through a web interface.

Configure System

View batch jobs in the queue, track processing status, and monitor job completion.

View Queue

View complete job history with statistics, filtering, and detailed analytics for all processed batches.

View History

Train custom models from curated datasets, manage training jobs, and deploy fine-tuned models.

Open Dashboard

Interactive API documentation with examples for submitting batches, checking status, and more.

View API Docs

📄 llm.txt - Complete Reference

Single-file documentation with everything: quick start, troubleshooting, API reference, emergency procedures

Download
✅ STATUS.md - Quick Status Check

Current server status, quick fixes for common problems, access points

Download
🔧 SYSTEM_MANAGEMENT.md - Detailed Guide

Comprehensive management guide with troubleshooting, integration examples, GPU monitoring

Download
📘 README.md - Project Overview

Project overview, features, architecture, and getting started guide

Download

Health Check Check if server is running Available Models List all loaded models System Status (JSON) Get detailed system status List Batches View all batch jobs

If the system is not responding, run this command on the server:

./scripts/restart_server.sh

Or use the Admin Panel to restart the worker or clear GPU memory.