QuoxGPU
GPU Fleet Monitoring and Inference Management
Standalone daemon for GPU machines. Monitors NVIDIA hardware via NVML, discovers inference backends (Ollama, vLLM, llama.cpp, NIM), and reports to QuoxCORE. Single binary, zero dependencies.
Nothing charged today: the installer is not live yet, and we contact you at release.
Hardware Visibility Without the Guesswork
QuoxGPU detects NVIDIA GPUs via the NVML library at runtime. No compile-time dependencies, no driver version coupling. Falls back to nvidia-smi CLI parsing in containers where the NVML shared library is not mounted.
VRAM usage, temperature, fan speed, power draw, utilisation, and PCI bus identity for every GPU on the host. Readings are cached with a configurable TTL to avoid hammering the driver.
- NVML detection (primary) with nvidia-smi fallback
- Per-GPU VRAM, temperature, power, utilisation
- PCI bus and UUID identification
- Automatic no-GPU mode for inference-only hosts
What QuoxGPU Does
GPU Hardware Monitoring
VRAM, temperature, fan speed, power draw, and utilisation for every NVIDIA GPU on the host. Detects unhealthy devices automatically.
Backend Auto-Detection
Probes configured URLs and identifies whether they run Ollama, vLLM, llama.cpp, or NVIDIA NIM. No manual type configuration required.
Model Inventory
Lists all available and loaded models across every backend. Shows VRAM allocation per model on Ollama, loaded status on vLLM and NIM.
Heartbeat Reporting
Sends GPU state, backend health, and model inventory to QuoxCORE collector every 30 seconds. Same protocol as QuoxAgent.
Prometheus Metrics
Exposes /metrics endpoint for Prometheus scraping. GPU utilisation, VRAM usage, temperature, and backend health as standard gauge metrics.
Thermal Monitoring
Reports degraded status when GPU temperature exceeds 90C. Visible in the fleet dashboard before hardware damage occurs.
Four Backends, One Interface
Configure backend URLs in a single YAML file. QuoxGPU auto-detects the backend type by probing health and model endpoints in priority order: Ollama, vLLM, llama.cpp, NVIDIA NIM.
Each backend is probed for health status, version, and loaded models. Ollama reports available vs running models with VRAM allocation. vLLM and NIM expose one model per process. llama.cpp reports slot status.
- Ollama: /api/tags, /api/ps, /api/version
- vLLM: /health, /v1/models, /metrics
- llama.cpp: /health, /slots
- NVIDIA NIM: /v1/health/ready, /v1/models
Choose Your Edition
QuoxGPU is open source. Premium tiers add fleet management and audit features via QuoxCORE.
One Binary, One Config, Done
QuoxGPU is a single Go binary with no runtime dependencies. Download it, write a YAML config pointing at your inference backends and QuoxCORE collector, and start the systemd service.
Cross-compiled for Linux amd64 and arm64. The systemd service file includes security hardening: ProtectSystem=strict, NoNewPrivileges, and GPU device access restricted to /dev/nvidia*.
How It Fits Together
Standalone Daemon
Not a QuoxAgent plugin. Separate binary, separate release cycle, separate install. Runs alongside QuoxAgent or independently.
Cached Readings
GPU and backend data cached with configurable TTL (default 5s). Prevents hammering NVML or backend health endpoints under concurrent requests.
Systemd Hardened
ProtectSystem=strict, NoNewPrivileges, PrivateTmp, DeviceAllow restricted to NVIDIA devices. Runs as dedicated quox user.
Graceful Degradation
No GPU? Runs in inference-only mode. No backends? Runs in GPU-only mode. No collector? Runs standalone with local API.
See every GPU. Know every model.
QuoxGPU runs on each GPU machine and reports hardware state, loaded models, and backend health to QuoxCORE. One binary, one config file, full visibility. The installer is not live yet, so nothing is charged today: reserve now and we contact you at release.
Stay updated
Product updates, new features, and protocol news.