ai - 9 min read
Jesse Williams
95 posts by Jesse Williams
ai - 18 min read
Accelerate Local AI Inference with Speculative Decoding on Jozu RIC
Learn how speculative decoding pairs a small draft model with a large target model to speed up local LLM inference, and how to run it with Jozu Rapid Inference Containers.
ai - 8 min read
Your Organization Is Further Along the AI Curve Than You Think. That’s the Problem.
Recap of our webinar with Jozu CEO Brad Micklea: the five levels of AI adoption, the two gaps that get organizations hurt (the AI supply chain and the runtime), real-world attacks, and four actions to take this quarter.
ai - 7 min read
The OWASP Top 10 for Agentic Applications 2026: What It Means for Teams Running Agents in Production
KitOps - 7 min read
Run Qwen3 4B on 60% of a GPU with HAMi and KitOps
Run a Qwen3 4B model on a fractional GPU slice on Kubernetes, with the vLLM server and weights shipped as one signed, reproducible OCI artifact. A walkthrough using Project HAMi for GPU virtualization and KitOps for model packaging.
ai - 5 min read