Documentation.
Quickstart, supported hardware, and inference backends. Full deployment guides delivered with our engineering team.
[ Getting Started ]
01
Quickstart
Pull the container, serve a model, call the API. No account, no licence key. Running in minutes.
02
CLI reference
Every command, every flag. Lives inside the binary so it always matches your version.
03
Deployment guides
Hardware audits, air-gapped installs, production hardening. Delivered with our forward-deployed engineering team.
Talk to the team[ Hardware ]
Supported hardware.
Sector88 runs on a wide range of machines. One install across every major hardware family.
NVIDIA CUDA
RTX 30/40/50, A-series, L-series, H100, H200, Jetson
AMD ROCm
MI250X, MI300X accelerators
Intel
Gaudi 2, Gaudi 3, Xeon CPUs
Qualcomm
Cloud AI 100 accelerators
Apple Silicon
M-series via Metal
CPU-only
x86 and ARM, server and edge
Google TPU
v4 / v5e, via vendor runtime
Custom silicon
On request, forward-deployed
If a machine is not listed, it probably still works. Sector88 falls back to a CPU path on anything without a native backend.
[ Backends ]
Inference backends.
The engines you already trust run on Sector88. It picks the right backend for each machine and keeps it in sync across a fleet.
llama.cpp
GGUF, CPU + GPU, edge
vLLM
PagedAttention, throughput
Native
PyTorch, direct path
TensorRT-LLM
NVIDIA datacentre path
Custom backends
Per-deployment via engineering
[ API ]
API shape.
OpenAI-compatible. Point any client at your Sector88 node instead of api.openai.com.
# Chat completions
POST /v1/chat/completions
# Models
GET /v1/models
# Completions (legacy)
POST /v1/completions
# Embeddings
POST /v1/embeddings
# Health
GET /health
Need deployment guides?
Production hardening, roles and audit, air-gapped installs. Delivered with the engineering team.