# google-ai-edge

> Open-source publisher. Listings imported from github.com/google-ai-edge — credited to the original author with their license.

- **Listings:** 4
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/google-ai-edge
- **Website:** https://github.com/google-ai-edge

## Published listings

- [Compiled Model App Scaffolding](https://agentstack.voostack.com/l/skill-google-ai-edge-litert-samples-compiled-model-app-scaffolding) — Skill · Free · security-reviewed — `agentstack add skill-google-ai-edge-litert-samples-compiled-model-app-scaffolding`
  Build a new Android app (Kotlin, Compose) around a verified LiteRT model using the CompiledModel API - the app architecture, the inference-layer lifecycle rules, model delivery, and the UI traps that masquerade as model bugs. Use when turning a converted and device-verified model into a demo or product app, when an app's inference layer leaks memory or blocks the UI, or when a model that verified…
- [Gpu Clean Conversion](https://agentstack.voostack.com/l/skill-google-ai-edge-litert-samples-gpu-clean-conversion) — Skill · Free · security-reviewed — `agentstack add skill-google-ai-edge-litert-samples-gpu-clean-conversion`
  Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
- [On Device Verification](https://agentstack.voostack.com/l/skill-google-ai-edge-litert-samples-on-device-verification) — Skill · Free · security-reviewed — `agentstack add skill-google-ai-edge-litert-samples-on-device-verification`
  Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and diagnose device-only failures such as silent CPU fallback, whole-graph compile ceilings, and fp16 range breaks. Use after conversion or quantization, when device output is wrong or NaN, when a clean graph fails to compile only on d…
- [Accuracy Safe Quantization](https://agentstack.voostack.com/l/skill-google-ai-edge-litert-samples-accuracy-safe-quantization) — Skill · Free · security-reviewed — `agentstack add skill-google-ai-edge-litert-samples-accuracy-safe-quantization`
  Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.