No. 01
Uncategorised
How to configure vLLM for parallel request handling
Parallel request handling in vLLM depends on how many requests the scheduler can run, how many tokens it…
20 Oct 2026
HotSourceTechnical Journal
Ideas, straight from the source■
No. 02
Uncategorised
How to configure llama.cpp for parallel request handling
To handle simultaneous requests in llama.cpp, start with llama-server and size its context and batching settings for the…
14 Oct 2026
No. 03
Uncategorised
Self host your own AI with Qwen 3.8
A local Qwen3.8-27B chat and API endpoint can run on your own computer with Ollama, provided the build…
12 Oct 2026
03 / Studio
We’re an independent technology journal fascinated by the uptake of AI and inferencing in both everyday life and in the office. We discuss all things software, self-hosting, programming and scaling, and everything in-between.
We’re affiliated with Infersec.ai, a European sovereign AI platform where you bring your own hardware/compute to manage your inferencing fabric in a secure and scalable environment.
HotSource is based in Finland.