QVAC Blog

6 July 2026 — Fabric, formally qvac-fabric-llm.cpp, is QVAC’s maintained fork of llama.cpp. It keeps compatibility with upstream llama.cpp while adding QVAC-specific capabilities such as TurboQuant KV-cache quantization, mobile GPU optimizations, BitNet support, and native LoRA fine-tuning across CPU, Vulkan, and Metal. Inside QVAC, Fabric is the native engine that powers @qvac/llm-llamacpp. It is the layer that executes LLM […]

17 March 2026 — The world’s first framework to enable BitNet fine-tuning with LoRA on GPUs enabling fine-tuning on edge devices substantial performance improvements

1 December 2025 — We present a unified, cross-platform framework that successfully enables parameter-efficient training of modern LLMs with LoRA on consumer hardware such as mobile SoCs and desktop GPUs, without relying on a CUDA-only ecosystem.