Artificial Intelligence

All Blogs

Using llama.cpp to deploy LLMs on Intel GPUs

by Jon Shah | Oct 19, 2025 | Artificial Intelligence | 0 Comments

The open-source ecosystem around llama.cpp has transformed it from a small learning experiment into one of the most active lightweight LLM engines available today. Built for speed and tinkering, the...

Automating a SQL smoke test

by Jon Shah | Jun 19, 2025 | Az DevOps, PowerShell | 0 Comments

In modern database development workflows, updates to the schema and data should be tested, so they don't introduce bugs or cause data loss. This testing can sometimes be referred to as a smoke test,...

Clone a dedicated SQL pool between encrypted and resource locked Synapse workspaces

by Jon Shah | Apr 10, 2025 | Az Synapse, Az DevOps | 0 Comments

This post covers the automation of cloning a Synapse dedicated SQL pool from one workspace to another where locks and encryption exist. The steps required by the code are as...

Gracefully delete all pipelines from a Synapse workspace that has pipeline to pipeline dependencies

by Jon Shah | Mar 18, 2025 | Az Synapse | 0 Comments

As you build out a Synapse workspace, you will inevitably start to create a dependency model between pipelines. When deploying artefacts to the workspace, you may need to clear down the existing...

This Blog

Using llama.cpp to deploy LLMs on Intel GPUs

Oct 19, 2025

The open-source ecosystem around llama.cpp has transformed it from a small learning experiment into one of the most active lightweight LLM engines available today. Built for speed and ...

No results found.