Real-World Case Studies & Best Practices

Building customer-facing NPU agents (chatbots, assistants). Batch vs. streaming inference strategies. Handling fallbacks and graceful degradation. Lessons learned and anti-patterns to avoid.

5.1 What's Actually Shipping on Intel NPUs

The most useful thing a book like this can do, in its closing chapter, is be honest about what is...

5.2 A Worked Agentic Translation Assistant

This section ties the book together by walking through an end-to-end agentic translation assistan...

5.3 Anti-Patterns and Lessons

We've covered foundations, state, tools, deployment, and case studies. This final section pulls t...

1.1 Understanding NPU Architecture

1.2 Computational Constraints & Model Optimization

1.3 Latency, Throughput, and Hardware-Aware Patterns

1.4 The Accuracy Cost of Quantization

1.5 Speculative Decoding

2.1 Context Windows and the Memory Wall

2.2 KV Cache Engineering: Reuse, Eviction, and Prefix Sharing

2.3 Reasoning Loops Under Constraint

3.1 Designing Tools for NPU-Bound Agents

3.2 Local-NPU vs Cloud Tools: A Real Trade-Off Table

3.3 Multi-Device Orchestration on a Single SoC

3.4 Structured Outputs and Constrained Decoding

4.1 Serving NPU Models with OVMS

4.2 Telemetry: What Works, What Doesn't, and What's Missing

4.3 A/B Testing, Canaries, and Hotswaps

4.4 Security and Privacy on the Edge

5.1 What's Actually Shipping on Intel NPUs

5.2 A Worked Agentic Translation Assistant

5.3 Anti-Patterns and Lessons

Glossary

References

Real-World Case Studies & Best Practices

5.1 What's Actually Shipping on Intel NPUs

5.2 A Worked Agentic Translation Assistant

5.3 Anti-Patterns and Lessons

Search Results