Crate autoagents_llamacpp 

AutoAgents llama.cpp Backend

Local LLM inference backend for AutoAgents using llama-cpp-2 bindings.

Features

• GGUF Model Support: Load local GGUF models via llama.cpp
• Sampling Controls: Temperature, top-k, top-p, penalties
• Structured Output: JSON schema hints with optional grammar enforcement
• Streaming: Token streaming for chat responses
• Production Ready: Robust error handling and configuration

Re-exports

pub use builder::LlamaCppProviderBuilder;

pub use config::LlamaCppConfig;

pub use config::LlamaCppConfigBuilder;

pub use config::LlamaCppReasoningFormat;

pub use config::LlamaCppSplitMode;

pub use error::LlamaCppProviderError;

pub use models::ModelSource;

pub use provider::LlamaCppProvider;

Modules

builder

config

Configuration structures for llama.cpp provider.

conversion

Type conversions between AutoAgents types and llama.cpp types.

error

Error handling and conversions for llama.cpp backend.

huggingface

HuggingFace GGUF resolver using hf-hub cache.

models

Model source definitions for llama.cpp backend.

provider

LlamaCppProvider implementation with LLMProvider traits.

Enums

LlamaSplitMode

A rusty wrapper around llama_split_mode.