Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/Nvidia
Maverick617
63 points
9 comments
October 01, 2026
Related Discussions
Found 5 related stories in 197.3ms across 13,334 title embeddings via pgvector HNSW
- Show HN: GPUWorks – A 40 MB GPU cluster manager for vLLM/SGLang, no K8s needed wangweinoo1 · 25 pts · November 04, 2026 · 60% similar
- Show HN: PantheonGPU – GPU health testing and AI workload benchmarking saqibkhan1992 · 13 pts · August 18, 2026 · 57% similar
- Show HN: Uji – Gentoo of Coding Agents cat-whisperer · 11 pts · October 29, 2026 · 56% similar
- Show HN: Jevman – AI decision models play Pac-Man felix089 · 52 pts · October 08, 2026 · 56% similar
- Show HN: IT Thinks – Build a GPU from a Single NAND Gate benbenhere · 12 pts · November 19, 2026 · 56% similar
Discussion Highlights (3 comments)
PcChip
I didn't see any benchmarks against vllm, sglang, exllama, etc
peddling-brink
> llama.cpp via Vulkan (AMD / Intel / NVIDIA) or CPU fallback I got excited about someone paying attention to intel. Oh well.
dlcarrier
From what I've seen, Vulkan adds a lot of overhead on Intel hardware.