Kernel-level engineering writing about serving LLM inference without a host operating system, from the cllm team at Cognisoc.https://cllm.cognisoc.com/en-ushttps://cllm.cognisoc.com/blog/why-a-unikernel-for-llm-serving/https://cllm.cognisoc.com/blog/why-a-unikernel-for-llm-serving/Inference servers spend a surprising number of cycles maintaining the operating system they run on. cllm is the experiment we ran to find out what happens when you delete almost all of it.Tue, 12 May 2026 00:00:00 GMThttps://cllm.cognisoc.com/blog/multiboot-pci-e1000-and-an-http-server/https://cllm.cognisoc.com/blog/multiboot-pci-e1000-and-an-http-server/A walk through the cllm boot path: how a Multiboot ELF hands off to C, claims an Intel e1000 NIC over PCI, and ends up answering HTTP requests with no operating system underneath.Wed, 22 Apr 2026 00:00:00 GMThttps://cllm.cognisoc.com/blog/the-four-phase-roadmap/https://cllm.cognisoc.com/blog/the-four-phase-roadmap/A walk through the project specification: how cllm goes from a Multiboot kernel that serves HTTP to a unikernel that runs llama.cpp on a GPU with vLLM-derived optimizations, and what is honest about each phase.Mon, 30 Mar 2026 00:00:00 GMT