ggml Ships 1.0.0

After years of rapid iteration under opaque build numbers, ggml — the tensor library at the core of llama.cpp, whisper.cpp, and stable-diffusion.cpp — shipped its first 1.0.0 release on November 13. The milestone removes deprecated APIs, bumps the RPC protocol to v9, and delivers broad backend improvements spanning CUDA FP8, Metal MoE fusion, Vulkan FlashAttention, and new kernels for Hexagon, OpenCL, and WebGPU.

Read more →