How-toUpdated 2026-07-01 · 9 min read · by RTXsparks Lab
Serving Llama 3.2 90B Vision with SGLang on RTX Spark
Production SGLang deployment of Llama 3.2 90B Vision on RTX Spark. Configs, systemd, TLS, observability.
Install
Install SGLang via pip/docker/apt as appropriate. Verify GPU visibility with nvidia-smi.
- # SGLang install
- # see SGLang docs
Config
Optimized SGLang config for Llama 3.2 90B Vision at Q4_K_S: batch, KV cache dtype, and parallelism knobs.
Systemd unit
[Unit] Description=SGLang for Llama 3.2 90B Vision — [Service] ExecStart=/usr/bin/sglang serve llama-3-2-90b-vision --port 8000 — Restart=always.
nginx + TLS
Terminate TLS at nginx with a Let's Encrypt cert, rate-limit at 20 req/s per IP, and proxy to the local SGLang port.
Observability
Scrape SGLang Prometheus metrics into Grafana; watch tokens_per_second, batch_size, and kv_cache_usage.
Frequently asked questions
Is SGLang the fastest for Llama 3.2 90B Vision?
It's the easiest, not always the fastest.
Can I run multiple models with one instance?
One process per model is standard.