mini-vllm-rs is a single-node LLM inference engine I built in Rust on top of Candle for macOS. It can...
When LLM Inference on CPU Beats Waiting for the GPU
Related
2,332 real phone calls later: five things I learned building an AI host for a restaurant
I build Hostly (hostly.ie), an AI host that answers the phone and WhatsApp for restaurants in...
Five read-only settings shrank an MCP tool list. Two did nothing.
Seven MCP servers started with and without a read-only setting: five tool lists got shorter by 9 to 40 tools, two did not change.
Treat Your AI Agents Like Code - GitOps for Azure AI Foundry Agents
If your team builds AI agents in Azure AI Foundry, you have probably lived this story: Someone...