#Onnx

CVE-2026-115920: Out-of-Bounds Read in ONNX ConvTranspose Shape Inference Vulnerability...

CVE-2026-115922: Denial of Service via Unchecked Expansion of Packed Sub-Byte Tensors in...

This post is the third of a three-part series. See also Model Quantization: Concepts, Methods, and Why It Matters and Model Quantization: Post-Training…

An Android app that declares no INTERNET permission cannot download models. That is the whole...

Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems.

When we shipped Auto Embeddings — the feature that turns any text column into a vector automatically, with no separate model service to run — the most common piece of feedback was about speed.

OpenCV 5 is here! A massive modernization brings a graph-based DNN engine, over 80% ONNX coverage, hardware acceleration, LLM/VLM support, and a faster Python-first core. Learn why this isn't just an incremental update.

From Dev.to - webdev: How to Deploy Phi-4 with ONNX Runtime on a $5/Month DigitalOcean Droplet: Lightweight Enterprise Inference at 1/200th Claude Cost

Note: This article documents work performed with AI assistance (Claude Sonnet 4.6 via Claude Code),...

From Dev.to - machinelearning: I built real-time glasses detection that runs entirely in the browser (ONNX + WebGPU)

In 2024, 68% of ML teams reported supply chain attacks targeting pre-trained Hugging Face models,...

Post 3 ended with three numbers: 97.4% test accuracy, 100% precision, 0 false positives. All of it...