Eve library

Phase 93 edge and on-device deployment

Other

Revision 1

On this page

The implementation is provider-neutral and fail-closed. Apple CoreML/MLX, Qualcomm QNN, MediaTek NeuroPilot, TensorRT, LiteRT/TFLite, ExecuTorch, MLC, WebLLM and WebGPU SDK calls enter through adapters; the core never reports a successful conversion without artifact integrity and quality evidence.

Capability map#

  • edge-compilation.ts: ONNX optimization and all target compilers, INT8 calibration requirements, validation, structured/unstructured pruning with fine-tuning, Axolotl QAT, teacher/student distillation, and supported SLM fine-tuning.
  • edge-runtime.ts: per-class budgets, device profiling and Pareto selection, quality-aware device/edge/cloud fallback, complete offline bundles, AES-256-GCM in-memory decryption, WebGPU/WebLLM selection, and battery/thermal scheduling.
  • edge-operations.ts: signed differential atomic updates, fleet telemetry and issue detection, device-vs-cloud promotion gates, and rollback-safe OTA CI/CD.

Production invariants#

Vendor adapters must pin SDK/compiler and target versions in artifact metadata. Real target-device profile evidence is mandatory before distribution. Model updates require a trusted manifest, patch/base/result hashes, staging and atomic activation. Offline mode requires model, tokenizer and vocabulary integrity. Encrypted cleartext is held only for runtime loading and must never be persisted or logged. Device experiment promotion requires quality parity while also improving latency and cost, and installation verification failure rolls back.