Recent Activity
Admin
User for 4 months
Recently Created Pages View All
4.4 Security and Privacy on the Edge
"It runs on the device, so it's private" is the marketing line. It's also a half-truth that has c...
3.4 Structured Outputs and Constrained Decoding
An agent is only as reliable as the parser that reads its output. Chapter 3.1 covered designing t...
1.5 Speculative Decoding
Chapter 1.3 established the bandwidth ceiling as the binding constraint on LLM decode: 136.5 GB/s...
1.4 The Accuracy Cost of Quantization
Chapter 1.2 laid out the quantization recipes Intel NPU supports: INT8-sym, INT4-sym group-128 or...
Preface
This book is about a narrow, awkward, increasingly important corner of applied AI: building agent...
Recently Created Chapters View All
Appendices
Glossary of terms and consolidated source references for the book.
Real-World Case Studies & Best Practices
Building customer-facing NPU agents (chatbots, assistants). Batch vs. streaming inference strateg...
Production Deployment & Observability
Model serving architectures (ONNX, TensorRT, TVM). Monitoring latency, throughput, and reliabilit...
Tool Use & Integration Patterns
Designing lightweight tools for NPU-based agents. Async I/O and non-blocking integrations. Local ...
Agent State & Decision-Making on Constrained Hardware
Managing agent context and memory within NPU limits. Efficient reasoning loops for low-latency in...
Recently Created Books View All
Recently Created Shelves
Admin has not created any shelves