cllm
A Multiboot C unikernel that boots on bare metal or QEMU and serves an llama.cpp-compatible HTTP API — the kernel is the application. Inference-engine integration is on the public roadmap.
Key Features
No Operating System
The kernel IS the application. Zero OS overhead, zero abstraction layers.
Custom Libc
Built-in malloc, snprintf, string ops — everything needed, nothing wasted.
PCI + e1000 NIC
PCI bus enumeration and Intel e1000 network driver for direct hardware access.
HTTP Server
Built-in HTTP server with REST API endpoints for inference requests.
llama.cpp Compatible
API endpoints compatible with the llama.cpp ecosystem.
QEMU + Bare Metal
Run in QEMU for development or boot directly on x86 hardware.
Quick Start
# Prerequisites
sudo apt-get install gcc gcc-multilib make qemu-system-x86
# Build and run
git clone https://github.com/cognisoc/cllm.git
cd cllm
make runSerial output appears on your terminal. Press Ctrl-A X to exit QEMU.
Architecture
+-----------------------------------------------------------+
| QEMU / Bare Metal (x86, Multiboot) |
+-----------------------------------------------------------+
| boot.S Multiboot entry, stack, serial init |
| kernel.c Kernel main, VGA terminal, serial I/O |
| memory.c Heap allocator (malloc/free) |
| string.c libc subset (snprintf, memcpy, ...) |
| network.c PCI enumeration + e1000 NIC driver |
| http.c HTTP server, request routing |
| api_v1.c llama.cpp-compatible REST API |
| llm.c Model loading and inference interface |
+-----------------------------------------------------------+The kernel boots via Multiboot, initializes serial and VGA output, brings up an e1000 network interface via PCI, and enters a packet-processing loop that serves HTTP requests for LLM inference.
Make Targets
| Target | Description |
|---|---|
make | Build release kernel (build/kernel.bin) |
make debug | Build with debug symbols |
make run | Build and boot in QEMU (serial on stdio) |
make run-vga | Build and boot in QEMU (VGA window) |
make run-debug | Build and boot paused for GDB on :1234 |
make clean | Remove build artifacts |
Roadmap
- Multiboot kernel with VGA + serial output
- Custom libc (malloc, snprintf, string ops)
- PCI enumeration and e1000 NIC driver
- HTTP server with REST API endpoints
- llama.cpp-compatible API (v1 endpoints)
- Integrate llama.cpp inference engine
- GPU passthrough (CUDA backend)
- Streaming token generation
- vLLM optimizations for transformer serving