Ggml-org merges webgpu Q2_0 support into llama.cpp

Q2_0 is a low‑bit quantization format that reduces model size and compute demand. By enabling it on WebGPU, developers can run quantized LLaMA‑style models directly in browsers or other WebGPU‑enabled environments with lower latency and memory usage. The merge was performed by contributor teddygood and passed the repository’s automated checks before being accepted.

The update expands the hardware back‑end options for ggml, which powers many open‑source LLM projects. It signals continued community effort to bring efficient inference to client‑side platforms, potentially widening access to large language models without relying on server‑side GPUs.