Crate llama_cpp_bindings 

Re-exports

pub use error::ApplyChatTemplateError;

pub use error::ChatTemplateError;

pub use error::DecodeError;

pub use error::EmbeddingsError;

pub use error::EncodeError;

pub use error::EvalMultimodalChunksError;

pub use error::GrammarError;

pub use error::JsonSchemaToGrammarError;

pub use error::KvCacheSeqAddError;

pub use error::KvCacheSeqDivError;

pub use error::LlamaContextLoadError;

pub use error::LlamaCppError;

pub use error::LlamaLoraAdapterInitError;

pub use error::LlamaLoraAdapterRemoveError;

pub use error::LlamaLoraAdapterSetError;

pub use error::LlamaModelLoadError;

pub use error::LogitsError;

pub use error::MarkerDetectionError;

pub use error::MetaValError;

pub use error::ModelParamsError;

pub use error::NewLlamaChatMessageError;

pub use error::ParseChatMessageError;

pub use error::Result;

pub use error::SampleError;

pub use error::SamplerAcceptError;

pub use error::SamplingError;

pub use error::StringToTokenError;

pub use error::TokenSamplingError;

pub use error::TokenToStringError;

pub use chat_message_parse_outcome::ChatMessageParseOutcome;

pub use llama_backend_device::LlamaBackendDevice;

pub use llama_backend_device::list_llama_ggml_backend_devices;

pub use llama_backend_device_type::LlamaBackendDeviceType;

pub use raw_chat_message::RawChatMessage;

pub use sampled_token::SampledToken;

pub use sampled_token_classifier::SampledTokenClassifier;

pub use sampled_token_section::SampledTokenSection;

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 ingest_prompt_chunk::ingest_prompt_chunk;

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_options::LogOptions;

pub use send_logs_to_log::send_logs_to_log;

Modules

batch_add_error

chat_message_parse_outcome

context

error

extract_tool_call_markers_from_haystack

ffi_error_reader

ffi_status_is_ok

ffi_status_to_i32

ggml_time_us

gguf_context

gguf_context_error

gguf_type

ingest_outcome

ingest_prompt_chunk

invalid_numa_strategy

json_schema_to_grammar

llama_backend

llama_backend_device

llama_backend_device_type

llama_backend_numa_strategy

llama_batch

llama_time_us

llama_token_attr

llama_token_attrs

llama_token_attrs_from_int_error

llguidance_sampler

log_options

max_devices

mlock_supported

mmap_supported

model

mtmd

raw_chat_message

resolved_tool_call_markers

sampled_token

sampled_token_classifier

sampled_token_section

sampling

send_logs_to_log

streaming_json_probe

streaming_markers

timing

token

tool_call_format

tool_call_marker_pair

tool_call_template_overrides

Structs

BracketedJsonShape

KeyValueXmlTagsShape

PairedQuoteShape

ParsedChatMessage

ParsedToolCall

ReasoningMarkers

TokenUsage

ToolCallMarkers

ToolCallValueQuote

XmlTagsShape

Enums

TokenUsageError

ToolCallArgsShape

ToolCallArguments