YOLO-ToysArchitecture Whitepaper

One runtime for heterogeneous vision models, documented like a systems paper.

YOLO-Toys unifies YOLOv8, DETR, OWL-ViT, Grounding DINO, and BLIP behind a single FastAPI plus WebSocket service boundary. This site treats the repository as a technical artifact: architecture atlas, design essays, operational references, and research context — documented to the standard of a systems whitepaper.

Start with the Primer Architecture Atlas API Reference GitHub

Runtime architecture

YOLO-Toys is organized as a normalized serving runtime: transport-specific ingress, a central control plane, registry-backed dispatch, and model-family adapters that keep heterogeneous execution localized.

5 model familiesREST + WebSocketHandler / Registry patternLRU + TTL cache

Runtime characteristics

<5msWarm latencyYOLOv8n on GPU, cache hit path

5Model familiesYOLO · DETR · OWL-ViT · G-DINO · BLIP

142Requests / secYOLOv8n cached, 20 concurrent users

85%Memory thresholdLRU eviction trigger for GPU safety

6Middleware layersSecurity → Metrics → Timeout → Rate → GZip → CORS

1Service boundaryAll model families behind one FastAPI runtime

API surfaceHTTP REST + WebSocket ingress — routes stay thin, transport-specific, and replaceableTransport

Middleware stackSecurityHeaders → Metrics → Timeout → RateLimit → GZip → CORS in layered orderCross-cutting

Runtime coreModelManager — cache policy, concurrency guardrails, lifecycle ownershipControl plane

Handler registryHandlerRegistry — category inference, model metadata, deterministic dispatchDispatch

Execution adaptersYOLO · DETR · OWL-ViT · Grounding DINO · BLIP handlers — model-specific logic localizedExecution

Result normalizationStable public schema across all model families — same envelope for YOLO and DETRContract

Reading tracks

Enter through architecture, operations, or research — each path is optimized for a different kind of expert reader.

The site is structured as a technical whitepaper with an academy and research wing. Every reading track is designed for advanced readers who want both the how and the why.

Operator / Integrator

Start in the primer to validate deployment assumptions, then move through API surfaces and operational references.

Open chapter

Contributor / Extender

Read the academy essays to understand handler and registry boundaries before writing code. Understand the why before the how.

Open chapter

Researcher / Reviewer

Start at the architecture overview, then use the research chapter for academic context, citations, and comparative analysis.

Open chapter