search
llama.cpp
Trends
- 1Janus runs GGUF language models on any GPU via Vulkan●Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
A developer has released Janus, an open-source tool written in Go that runs GGUF-format language models using Vulkan graphics drivers. It ships as a single binary and works across AMD, Intel and Nvidia GPUs, removing the need for vendor-specific CUDA tooling. Commenters are discussing its performance compared with llama.cpp and its appeal for users on non-Nvidia hardware.
Repos
- ollaya-dev/ollaya Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollam
- magnitudedev/magnitude Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on
- kvmem/kvmem-llama.cpp
- Vibra-Ingenn/Janus Janus is a API router for AI models written in Go and has a Vulkan Model runner
- Rizzo-AI-Academy/rizzo-flow The open, local take on Jev: typed decisions from an LLM, without generating a single token
- IterateAI/lifeboat-releases Lifeboat — downloads for macOS, Windows and Linux, plus Docker and Kubernetes install instructions. Run language models