List of all items

Structs

• context::LlamaContext
• context::params::LlamaContextParams
• context::session::LlamaStateSeqFlags
• context::session::SeqState
• gguf::GgufContext
• grammar::DryParams
• grammar::LlamaDrySampler
• grammar::LlamaGrammar
• llama_backend::LlamaBackend
• llama_batch::LlamaBatch
• model::LlamaModel
• model::chat::LlamaChatMessage
• model::chat::LlamaChatTemplate
• model::lora::LlamaLoraAdapter
• model::params::LlamaModelParams
• quantize::LlamaQuantizeParams
• sampling::LlamaSampler
• speculative::MtpSpeculative
• speculative::MtpSpeculativeParams
• speculative::MtpStep
• timing::LlamaTimings
• token::LlamaToken
• token::data::LlamaTokenData
• token::data_array::LlamaTokenDataArray

Enums

• LlamaError
• context::embeddings::EmbeddingsError
• context::kv_cache::KvCacheConversionError
• context::params::LlamaContextType
• context::session::LoadSeqStateError
• context::session::LoadSessionError
• context::session::SaveSeqStateError
• context::session::SaveSessionError
• context::session::StateSeqError
• gguf::GgufError
• grammar::DryInitError
• grammar::GrammarInitError
• grammar::JsonSchemaError
• model::AddBos
• model::chat::ApplyChatTemplateError
• model::chat::NewLlamaChatMessageError
• model::lora::LlamaLoraAdapterInitError
• model::lora::LlamaLoraAdapterRemoveError
• model::lora::LlamaLoraAdapterSetError
• quantize::QuantizeError
• speculative::MtpOpType

Functions

• gguf::type_name
• grammar::json_schema_to_grammar
• quantize::quantize

Type Aliases

• quantize::ftype::llama_ftype

Constants

• quantize::ftype::LLAMA_FTYPE_ALL_F32
• quantize::ftype::LLAMA_FTYPE_MOSTLY_BF16
• quantize::ftype::LLAMA_FTYPE_MOSTLY_F16
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ1_KT
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ1_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ1_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_KL
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_KS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_KT
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_XS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ2_XXS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_KL
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_KS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_KT
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ3_XXS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_KS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_KSS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_KT
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_NL
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ4_XS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ5_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ5_KS
• quantize::ftype::LLAMA_FTYPE_MOSTLY_IQ6_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q2_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q2_K_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q3_K_L
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q3_K_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q3_K_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q4_0
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q4_1
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q4_K_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q4_K_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q5_0
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q5_1
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q5_K_M
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q5_K_S
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q6_K
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q8_0
• quantize::ftype::LLAMA_FTYPE_MOSTLY_Q8_KV