llama-crab-sys 0.1.1

Low-level FFI bindings to llama.cpp, ggml, gguf and mtmd (autogenerated via bindgen + cmake)
docs.rs failed to build llama-crab-sys-0.1.1
Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.
Visit the last successful build: llama-crab-sys-0.1.300

Low-level FFI bindings to llama.cpp.

Generated at build time via [bindgen] over wrapper.h, which in turn includes the public C headers of llama.cpp, ggml and gguf.

This crate is unsafe by design: every public item is a thin extern "C" wrapper around a llama.cpp symbol. Use the safe llama-crab crate instead unless you need fine-grained control.

Features

Feature Description
common Compile libcommon.a (chat templates, JSON schema, OpenAI compat)
cuda NVIDIA CUDA backend
cuda-no-vmm CUDA without Virtual Memory Management
metal Apple Metal (default on macOS aarch64)
vulkan Vulkan backend
rocm AMD ROCm/HIP backend
openmp OpenMP parallel CPU backend (default)
dynamic-link Link against libllama as a shared object
system-ggml Use GGML from the system instead of the bundled copy
mtmd Multimodal (vision + audio) helpers
llguidance llguidance sampler (custom C-ABI vtable)
dynamic-backends Load GGML backends as shared objects at runtime