Low-level C tensor library for machine learning that powers local inference projects such as llama.cpp.
llama.cpp and its underlying tensor library ggml have both shipped 1.0 releases, signaling API stability, with llama.cpp removing 35 deprecated functions from its public header. SGLang also announced its 1.0 at its summit, marking broader engineering maturity for local inference and high-performance serving stacks.
ggml has released v1.0.0, marking the first formal versioned milestone for the tensor library underpinning the llama.cpp ecosystem. Its core value is a dependency-free C/C++ implementation spanning x86, ARM, RISC-V and more, with 2- to 8-bit integer quantization plus MXFP4 and NVFP4 microscaling formats and zero runtime memory allocation. For local-inference and edge-deployment developers, this signals long-term ecosystem stability.
llama.cpp and its underlying tensor library ggml have officially reached version 1.0.0, establishing a semantic versioning scheme that flags breaking changes to the public C API. The project now supports over 150 model architecture variants and mainstream speculative decoding methods, backed by expanded self-hosted CI runners across NVIDIA, AMD, Qualcomm, Arm, IBM and Intel hardware.