llama-cpp-bindings 0.4.2

llama.cpp bindings for Rust
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

//! Bindings to the llama.cpp library.
//!
//! As llama.cpp is a very fast moving target, this crate does not attempt to create a stable API
//! with all the rust idioms. Instead it provided safe wrappers around nearly direct bindings to
//! llama.cpp. This makes it easier to keep up with the changes in llama.cpp, but does mean that
//! the API is not as nice as it could be.
//!
//! # Feature Flags
//!
//! - `cuda` enables CUDA gpu support.
//! - `sampler` adds the [`context::sample::sampler`] struct for a more rusty way of sampling.

pub mod context;
pub mod error;
pub mod ffi_error_reader;
pub mod ffi_status_is_ok;
pub mod ffi_status_to_i32;
pub mod ggml_time_us;
pub mod gguf_context;
pub mod gguf_context_error;
pub mod gguf_type;
pub mod json_schema_to_grammar;
pub mod llama_backend;
pub mod llama_backend_device;
pub mod llama_backend_numa_strategy;
pub mod llama_batch;
pub mod llama_time_us;
#[cfg(feature = "llguidance")]
pub mod llguidance_sampler;
pub mod log;
pub mod log_options;
pub mod max_devices;
pub mod mlock_supported;
pub mod mmap_supported;
pub mod model;
#[cfg(feature = "mtmd")]
pub mod mtmd;
pub mod openai;
pub mod sampling;
pub mod timing;
pub mod token;
pub mod token_type;

pub use error::{
    ApplyChatTemplateError, ChatParseError, ChatTemplateError, DecodeError, EmbeddingsError,
    EncodeError, GrammarError, LlamaContextLoadError, LlamaCppError, LlamaLoraAdapterInitError,
    LlamaLoraAdapterRemoveError, LlamaLoraAdapterSetError, LlamaModelLoadError, LogitsError,
    MetaValError, ModelParamsError, NewLlamaChatMessageError, Result, SampleError,
    SamplerAcceptError, SamplingError, StringToTokenError, TokenSamplingError, TokenToStringError,
};

pub use llama_backend_device::{
    LlamaBackendDevice, LlamaBackendDeviceType, list_llama_ggml_backend_devices,
};

pub use ffi_status_is_ok::status_is_ok;
pub use ffi_status_to_i32::status_to_i32;
pub use ggml_time_us::ggml_time_us;
pub use json_schema_to_grammar::json_schema_to_grammar;
pub use llama_time_us::llama_time_us;
pub use max_devices::max_devices;
pub use mlock_supported::mlock_supported;
pub use mmap_supported::mmap_supported;

pub use log::send_logs_to_tracing;
pub use log_options::LogOptions;

#[cfg(any(test, feature = "tests_that_use_llms"))]
pub mod test_model;