DEV Community

Intel edge AI notes - Inference you can measure and trust Series' Articles

Back to Shubham Anandani's Series
Packaging Inference for Production: A Checklist for Shipping an Optimized-Model Service
imshubh profile

Packaging Inference for Production: A Checklist for Shipping an Optimized-Model Service

#mlops #ai #devops #intel
Comments
4 min read
CPU-Only, By Design: Building an Edge-AI Service Without Assuming Accelerators
imshubh profile

CPU-Only, By Design: Building an Edge-AI Service Without Assuming Accelerators

#edgeai #ai #cpu #architecture
Comments
4 min read
Benchmarking Honestly: Building a Repeatable, Trustworthy Inference Benchmark
imshubh profile

Benchmarking Honestly: Building a Repeatable, Trustworthy Inference Benchmark

#benchmarking #ai #performance #intel
Comments
4 min read
The Conversion Gap: From ONNX Export to an Optimized Runtime Format
imshubh profile

The Conversion Gap: From ONNX Export to an Optimized Runtime Format

#onnx #machinelearning #ai #intel
Comments
4 min read
Faster Isn’t Free: The Real Trade-offs of Quantizing a Model from FP32 to INT8
imshubh profile

Faster Isn’t Free: The Real Trade-offs of Quantizing a Model from FP32 to INT8

#ai #machinelearning #performance #intel
Comments
4 min read