List of all items

Structs

• chat::ChatApplyParams
• chat::ChatParams
• chat::ChatTemplates
• chat::GrammarTrigger
• common::CommonParams
• common::common_sampler_params
• common_sampler::CommonSampler
• common_sampler::CommonSamplerParams
• common_sampler::ReasoningBudget
• context::LlamaContext
• context::memory_breakdown::MemoryBreakdownEntry
• context::params::LlamaContextParams
• context::perf::PerfContextData
• context::tensor_capture::CapturedTensor
• context::tensor_capture::TensorCapture
• context::tensor_transaction::TensorBatchRow
• context::tensor_transaction::TensorCallbackFailure
• context::tensor_transaction::TensorSelector
• context::tensor_transaction::TensorShape
• context::tensor_transaction::TensorTransaction
• context::tensor_transaction::TensorTransactionError
• context::tensor_transaction::TensorTransactions
• context::tensor_transaction::TransactionalTensorCapture
• eagle::Eagle3Session
• eagle::Eagle3SessionConfig
• fit::DeviceMemoryEntry
• fit::DeviceMemoryHyperParams
• fit::DeviceMemoryReport
• fit::FitParams
• fit::FitParamsResult
• ggml::GgmlAllocr
• ggml::GgmlBackend
• ggml::GgmlContext
• ggml::GgmlGraph
• ggml::GgmlTensor
• llama_backend::InvalidNumaStrategy
• llama_backend::LlamaBackend
• llama_batch::LlamaBatch
• model::LlamaBackendDevice
• model::LlamaBackendDevices
• model::LlamaChatMessage
• model::LlamaLoraAdapter
• model::LlamaModel
• model::LlamaVocab
• model::params::LlamaModelParams
• model::params::kv_overrides::KvOverrideValueIterator
• model::params::kv_overrides::KvOverrides
• mtmd::MtmdAudioGen
• mtmd::MtmdAudioRequest
• mtmd::MtmdBatch
• mtmd::MtmdBitmap
• mtmd::MtmdCaps
• mtmd::MtmdContext
• mtmd::MtmdContextParams
• mtmd::MtmdDecoderPos
• mtmd::MtmdGenAudioInfo
• mtmd::MtmdImageTokens
• mtmd::MtmdInputChunk
• mtmd::MtmdInputChunks
• mtmd::MtmdInputText
• mtmd::MtmdLazyBitmap
• mtmd::MtmdVideo
• mtmd::MtmdVideoInfo
• mtmd::MtmdVideoParams
• mtmd::OwnedMtmdInputChunk
• mtp::MtpSession
• mtp::MtpSessionConfig
• ngram::NgramCache
• ngram::NgramMap
• quantize::Imatrix
• quantize::ImatrixEntry
• quantize::KvOverride
• quantize::QuantModelDesc
• quantize::QuantPreview
• quantize::QuantizeParams
• quantize::TensorTypeOverride
• rpc::backend::RpcBackend
• runtime::SpeculativeType
• sampling::LlamaSampler
• sampling::LlamaSamplerParams
• token::LlamaToken
• token::data::LlamaTokenData
• token::data_array::LlamaTokenDataArray
• token::detokenizer::StreamDetokenizer
• token_type::LlamaTokenAttrs

Enums

• ApplyChatTemplateError
• ChatTemplateError
• DecodeError
• EmbeddingsError
• EncodeError
• LLamaCppError
• LlamaContextLoadError
• LlamaLoraAdapterInitError
• LlamaLoraAdapterRemoveError
• LlamaLoraAdapterSetError
• LlamaModelLoadError
• NewLlamaChatMessageError
• StringFromModelError
• StringToTokenError
• TokenToStringError
• chat::ReasoningFormat
• chat::ToolChoice
• common_sampler::CommonSamplerType
• common_sampler::GrammarSource
• common_sampler::ReasoningBudgetState
• context::kv_cache::KvCacheConversionError
• context::params::LlamaAttentionType
• context::params::LlamaContextType
• context::params::LlamaFlashAttnType
• context::params::LlamaPoolingType
• context::params::ParamsCloneError
• context::params::RopeScalingType
• context::session::LoadSessionError
• context::session::SaveSessionError
• context::tensor_transaction::CapturedTensorData
• context::tensor_transaction::TensorAccess
• context::tensor_transaction::TensorDataMut
• context::tensor_transaction::TensorElementType
• context::tensor_transaction::TensorFiniteValidation
• context::tensor_transaction::TensorRowMapping
• context::tensor_transaction::TensorWriteback
• eagle::Eagle3SessionError
• fit::DeviceMemoryError
• fit::FitParamsError
• llama_backend::NumaStrategy
• llama_batch::BatchAddError
• model::AddBos
• model::LlamaBackendDeviceType
• model::LlamaTokenTypeFromIntError
• model::Special
• model::VocabType
• model::params::LlamaLazyMode
• model::params::LlamaLoadMode
• model::params::kv_overrides::ParamOverrideValue
• mtmd::MtmdAudioOutType
• mtmd::MtmdError
• mtmd::MtmdGenAudioType
• mtmd::MtmdInputChunkType
• mtmd::MtmdInputPart
• mtmd::MtmdLazyChunk
• mtmd::MtmdVideoItem
• mtp::MtpSessionError
• quantize::FtypeNameError
• quantize::GgmlType
• quantize::KvOverrideValue
• quantize::LlamaFtype
• quantize::QuantPreviewError
• rpc::error::RpcError
• speculative::SpeculativeStateError
• token::detokenizer::DetokenizeError
• token_type::LlamaTokenAttr
• token_type::LlamaTokenTypeFromIntError

Traits

• context::tensor_transaction::TensorTransactionHandler

Functions

• chat::format_name
• chat::json_schema_to_grammar
• chat::parse_messages_oaicompat
• chat::parse_tools_oaicompat
• fit::fit_params
• fit::get_device_memory_data
• flash_attn_type_name
• ggml::buffer_free
• ggml::graph_overhead
• ggml::is_quantized
• ggml::tensor_get
• ggml::tensor_overhead
• ggml::tensor_set
• ggml::type_name
• ggml_time_us
• llama_supports_mlock
• llama_time_us
• llama_version
• log_get
• log_set
• max_devices
• max_parallel_sequences
• max_tensor_buft_overrides
• mlock_supported
• mmap_supported
• model_meta_key_str
• model_quantize
• mtmd::mmproj_caps
• ngram::ngram_cache_draft
• ngram::ngram_simple_draft
• opt_epoch
• opt_init
• opt_param_filter_all
• print_system_info
• quantize::attn_rot_disabled
• quantize::set_attn_rot_disabled
• rpc::server::add_rpc_server
• rpc::server::serve
• runtime::download::list_cached_json
• runtime::download::remove_cached
• runtime::download::resolve_docker
• runtime::download::resolve_hf
• runtime::download::split_repo_tag
• runtime::log::pause
• runtime::log::resume
• runtime::log::set_colors
• runtime::log::set_file
• runtime::log::set_jsonl
• runtime::log::set_prefix
• runtime::log::set_timestamps
• runtime::log::set_verbosity
• runtime::log::verbosity_for_level
• runtime::speculative_types_from_gguf
• supports_gpu_offload
• supports_rpc
• token::from_vec_token_sys
• token::to_vec_token_sys

Type Aliases

• Result
• chat::ChatError
• common::common_sampler_type
• common_sampler::CommonSamplerError
• common_sampler::CommonSamplerScalars
• eagle::DFlashSession
• ggml::ggml_type
• mtmd::MtmdProgressCallback
• mtmd::Result
• ngram::NgramError
• runtime::RuntimeError

Constants

• common::COMMON_SAMPLER_TYPE_ADAPTIVE_P
• common::COMMON_SAMPLER_TYPE_DRY
• common::COMMON_SAMPLER_TYPE_INFILL
• common::COMMON_SAMPLER_TYPE_MIN_P
• common::COMMON_SAMPLER_TYPE_NONE
• common::COMMON_SAMPLER_TYPE_PENALTIES
• common::COMMON_SAMPLER_TYPE_TEMPERATURE
• common::COMMON_SAMPLER_TYPE_TOP_K
• common::COMMON_SAMPLER_TYPE_TOP_N_SIGMA
• common::COMMON_SAMPLER_TYPE_TOP_P
• common::COMMON_SAMPLER_TYPE_TYPICAL_P
• common::COMMON_SAMPLER_TYPE_XTC
• context::tensor_transaction::MAX_RETAINED_TENSOR_BYTES
• context::tensor_transaction::MAX_TENSOR_ELEMENTS
• context::tensor_transaction::MAX_TENSOR_FAILURE_BYTES
• context::tensor_transaction::MAX_TENSOR_NAME_BYTES
• context::tensor_transaction::MAX_TENSOR_ROWS
• context::tensor_transaction::MAX_TENSOR_SELECTORS
• speculative::MAX_SPECULATIVE_DRAFT_TOKENS
• speculative::MAX_SPECULATIVE_PROMPT_TOKENS
• speculative::MAX_SPECULATIVE_SEQUENCES
• speculative::MAX_SPECULATIVE_STATE_BYTES