> Markdown version of [/@technicallylegare](https://www.wearedevelopers.com/@technicallylegare). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# @technicallylegare
Open-source engineer at Red Hat focused on accessible AI and efficient LLM deployment.

## About

Legare Kerrison makes large language models cheaper and easier to run. As an open-source engineer and developer advocate on Red Hat's AI team, she builds tools for deploying artificial intelligence efficiently.

Her work centers on breaking down AI barriers. She regularly covers how to optimize LLM inference with vLLM to cut GPU costs, alongside approaches for tuning foundation models on consumer-grade hardware using InstructLab. Her priority is making technical complexity digestible.

Based in Boston, Legare is a tree hugger and an avid matcha fan.


## Upcoming Sessions

### World Congress 2026 North America · September 23, 2026
San José, CA
- [Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1415-fast-cheap-and)


## Past Sessions

### World Congress 2024 · July 17, 2024
Berlin, Germany
- [Unlocking the Power of AI: Accessible Language Model Tuning for All](https://www.wearedevelopers.com/videos/951-unlocking-the-power-of-ai-accessible-language-model-tuning-for-all) · 30 min · 🎥 Watch recording



## Videos

- [Unlocking the Power of AI: Accessible Language Model Tuning for All](https://www.wearedevelopers.com/videos/951-unlocking-the-power-of-ai-accessible-language-model-tuning-for-all) · Cedric Clyburn, @technicallylegare


## Links

- [LinkedIn](https://www.linkedin.com/in/legare-kerrison/)