> Markdown version of [/@adolf-hohl](https://www.wearedevelopers.com/@adolf-hohl). 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).

---

# Adolf Hohl
Builds efficient AI infrastructure and inference solutions for automotive enterprises.

## About

Adolf designs AI infrastructure for automotive enterprise customers across Europe. He works to ensure AI workloads run efficiently at scale, building out the systems required to train and deploy models in modern datacenters.

Much of his work centers on inferencing and GPU-accelerated large language models. During his talk on efficient LLM deployment, he broke down how to serve models across multi-GPU environments using TensorRT-LLM and Triton Inference Server. He likes taking inference solutions out of the lab and seeing them operate in the real world.



## Past Sessions

### World Congress 2024 · July 17, 2024
Berlin, Germany
- [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms) · 30 min · 🎥 Watch recording



## Videos

- [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms) · Adolf Hohl