Index
| abort_callback | Llama.Internal.Types.Params |
| abort_callback_data | Llama.Internal.Types.Params |
| accept | Llama.Internal.Types |
| acceptTokenWithSampler | Llama.Sampler |
| AdapterLora | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| AddBos | Llama.Internal.Types |
| addSamplerToChain | Llama.Sampler |
| allowRequantize | Llama.Internal.Types.Params |
| Always | Llama.Internal.Types |
| apply | Llama.Internal.Types |
| applyAdapterCVec | Llama.Adapter |
| applySampler | Llama.Sampler |
| areEmbeddingsEnabled | Llama.Decode |
| attention_type | Llama.Internal.Types.Params |
| Batch | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| batchGetOne | Llama.Decode |
| batchInit | Llama.Decode |
| bias | Llama.Internal.Types |
| cb_eval | Llama.Internal.Types.Params |
| cb_eval_user_data | Llama.Internal.Types.Params |
| cells | Llama.Internal.Types |
| cells_sequences | Llama.Internal.Types |
| chatApplyTemplate | Llama.ChatTemplate |
| chatContent | Llama.ChatTemplate |
| chatGetBuiltinTemplates | Llama.ChatTemplate |
| ChatMessage | |
| 1 (Type/Class) | Llama.ChatTemplate |
| 2 (Data Constructor) | Llama.ChatTemplate |
| chatRole | Llama.ChatTemplate |
| checkTensors | Llama.Internal.Types.Params |
| clearAdapterLora | Llama.Adapter |
| CLlamaAdapterLora | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| CLlamaContext | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| CLlamaContextParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| CLlamaKVCache | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| CLlamaModel | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| CLlamaModelParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| CLlamaModelQuantizeParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| CLlamaSamplerChainParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| CLlamaVocab | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| clone | Llama.Internal.Types |
| cloneSampler | Llama.Sampler |
| content | Llama.Internal.Types |
| Context | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| ContextParamsPtr | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| ctx | Llama.Internal.Types |
| c_llama_adapter_lora_free | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_adapter_lora_init | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_apply_adapter_cvec | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_backend_free | Llama.Internal.Foreign.Backend, Llama.Internal.Foreign |
| c_llama_backend_init | Llama.Internal.Foreign.Backend, Llama.Internal.Foreign |
| c_llama_batch_free_wrap | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_batch_get_one_into | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_batch_init_into | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_chat_apply_template | Llama.Internal.Foreign.ChatTemplate, Llama.Internal.Foreign |
| c_llama_chat_builtin_templates | Llama.Internal.Foreign.ChatTemplate, Llama.Internal.Foreign |
| c_llama_clear_adapter_lora | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_context_default_params_into | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| c_llama_decode_wrap | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_detach_threadpool | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| c_llama_detokenize | Llama.Internal.Foreign.Tokenize, Llama.Internal.Foreign |
| c_llama_encode | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_free | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_get_embeddings | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_get_embeddings_ith | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_get_embeddings_seq | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_get_kv_self | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| c_llama_get_logits | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_get_logits_ith | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_get_model | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_init_from_model_wrap | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_kv_cache_view_free | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_cache_view_init_into | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_cache_view_update | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_can_shift | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_clear | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_defrag | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_n_tokens | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_add | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_cp | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_div | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_keep | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_pos_max | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_seq_rm | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_update | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_kv_self_used_cells | Llama.Internal.Foreign.KVCache, Llama.Internal.Foreign |
| c_llama_log_set | Llama.Internal.Foreign.Split, Llama.Internal.Foreign |
| c_llama_model_chat_template | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_decoder_start_token | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_default_params | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_desc | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_free | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_get_vocab | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_has_decoder | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_has_encoder | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_is_recurrent | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_load_from_file_wrap | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_load_from_splits | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_meta_count | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_meta_key_by_index | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_meta_val_str | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_meta_val_str_by_index | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_ctx_train | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_embd | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_head | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_head_kv | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_layer | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_n_params | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_quantize | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_quantize_default_params | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_rope_freq_scale_train | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_rope_type_into | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_model_size | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| c_llama_n_threads | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_n_threads_batch | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_n_vocab | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_perf_context | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_perf_context_print | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_perf_context_reset | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_perf_sampler | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_perf_sampler_print | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_perf_sampler_reset | Llama.Internal.Foreign.Performance, Llama.Internal.Foreign |
| c_llama_pooling_type_into | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| c_llama_print_system_info | Llama.Internal.Foreign.Split, Llama.Internal.Foreign |
| c_llama_rm_adapter_lora | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_sampler_accept | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_apply | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_add | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_default_params_into | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_get | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_init | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_n | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_chain_remove | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_clone | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_free | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_get_seed | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_dist | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_dry | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_grammar | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_grammar_lazy_patterns | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_greedy | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_infill | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_logit_bias | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_min_p | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_mirostat | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_mirostat_v2 | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_penalties | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_temp | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_temp_ext | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_top_k | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_top_n_sigma | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_top_p | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_typical | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_init_xtc | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_name | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_reset | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_sampler_sample | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| c_llama_set_abort_callback | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_set_adapter_lora | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| c_llama_set_causal_attn | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_set_embeddings | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_set_n_threads | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_set_warmup | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_split_path | Llama.Internal.Foreign.Split, Llama.Internal.Foreign |
| c_llama_split_prefix | Llama.Internal.Foreign.Split, Llama.Internal.Foreign |
| c_llama_state_get_data | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_get_size | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_load_file | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_save_file | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_seq_get_data | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_seq_get_size | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_seq_load_file | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_seq_save_file | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_seq_set_data | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_state_set_data | Llama.Internal.Foreign.State, Llama.Internal.Foreign |
| c_llama_synchronize | Llama.Internal.Foreign.Decode, Llama.Internal.Foreign |
| c_llama_tokenize | Llama.Internal.Foreign.Tokenize, Llama.Internal.Foreign |
| c_llama_token_to_piece | Llama.Internal.Foreign.Tokenize, Llama.Internal.Foreign |
| c_llama_vocab_bos | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_eos | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_eot | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_mid | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_pad | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_pre | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_rep | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_sep | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_fim_suf | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_get_add_bos | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_get_add_eos | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_get_attr | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_get_score | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_get_text | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_is_control | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_is_eog | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_nl | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_n_tokens | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_pad | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_sep | Llama.Internal.Foreign.Vocab, Llama.Internal.Foreign |
| c_llama_vocab_type | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| data_ | Llama.Internal.Types |
| decodeBatch | Llama.Decode |
| defaultContextParams | Llama.Context |
| defaultModelParams | Llama.Model |
| defaultQuantizeParams | Llama.Model |
| defaultSamplerChainParams | Llama.Sampler |
| defrag_thold | Llama.Internal.Types.Params |
| detachThreadPool | Llama.Context |
| detokenize | Llama.Tokenize |
| devices | Llama.Internal.Types.Params |
| embd | Llama.Internal.Types |
| embeddings | Llama.Internal.Types.Params |
| encodeBatch | Llama.Decode |
| flash_attn | Llama.Internal.Types.Params |
| freeBatch | Llama.Decode |
| free_ | Llama.Internal.Types |
| fromLlamaRopePoolingType | Llama.Internal.Types.Params |
| fromLlamaRopeTypeScaling | Llama.Internal.Types.Params |
| fromLlamaRopeVocabType | Llama.Internal.Types.Params |
| ftype | Llama.Internal.Types.Params |
| getBatchSize | Llama.Context |
| getBatchThreadCount | Llama.Decode |
| getContextModel | Llama.Model |
| getContextPerformance | Llama.Performance |
| getContextSize | Llama.Context |
| getMaxDevices | Llama.Context |
| getMaxSeqCount | Llama.Context |
| getModelChatTemplate | Llama.Model |
| getModelDecoderStartToken | Llama.Model |
| getModelDescription | Llama.Model |
| getModelEmbeddingDim | Llama.Model |
| getModelHasDecoder | Llama.Model |
| getModelHasEncoder | Llama.Model |
| getModelIsRecurrent | Llama.Model |
| getModelMetaCount | Llama.Model |
| getModelMetaKeyByIndex | Llama.Model |
| getModelMetaValue | Llama.Model |
| getModelMetaValueByIndex | Llama.Model |
| getModelNumHeads | Llama.Model |
| getModelNumKVHeads | Llama.Model |
| getModelNumLayers | Llama.Model |
| getModelNumParams | Llama.Model |
| getModelRoPEFreqScale | Llama.Model |
| getModelRopeType | Llama.Model |
| getModelSize | Llama.Model |
| getModelTrainingContextSize | Llama.Model |
| getModelVocab | Llama.Model |
| getPoolingType | Llama.Context |
| getSamplerChainLength | Llama.Sampler |
| getSamplerFromChain | Llama.Sampler |
| getSamplerName | Llama.Sampler |
| getSamplerPerformance | Llama.Performance |
| getSamplerSeed | Llama.Sampler |
| getSequenceStateSize | Llama.State |
| getStateData | Llama.State |
| getStateSize | Llama.State |
| getThreadCount | Llama.Decode |
| getTimeUs | Llama.Context |
| getUnbatchedSize | Llama.Context |
| getVocabAddBOSToken | Llama.Vocab |
| getVocabAddEOSToken | Llama.Vocab |
| getVocabBosToken | Llama.Vocab |
| getVocabEosToken | Llama.Vocab |
| getVocabEotToken | Llama.Vocab |
| getVocabFIMMiddleToken | Llama.Vocab |
| getVocabFIMPADToken | Llama.Vocab |
| getVocabFIMPrefixToken | Llama.Vocab |
| getVocabFIMSeparatorToken | Llama.Vocab |
| getVocabFIMSuffixToken | Llama.Vocab |
| getVocabNlToken | Llama.Vocab |
| getVocabPadToken | Llama.Vocab |
| getVocabSepToken | Llama.Vocab |
| getVocabSize | Llama.Vocab |
| getVocabTokenAttr | Llama.Vocab |
| getVocabTokenCount | Llama.Vocab |
| getVocabTokenScore | Llama.Vocab |
| getVocabTokenText | Llama.Vocab |
| getVocabType | Llama.Model |
| GgmlType | Llama.Internal.Types.Params |
| GGML_TYPE_BF16 | Llama.Internal.Types.Params |
| GGML_TYPE_COUNT | Llama.Internal.Types.Params |
| GGML_TYPE_F16 | Llama.Internal.Types.Params |
| GGML_TYPE_F32 | Llama.Internal.Types.Params |
| GGML_TYPE_F64 | Llama.Internal.Types.Params |
| GGML_TYPE_I16 | Llama.Internal.Types.Params |
| GGML_TYPE_I32 | Llama.Internal.Types.Params |
| GGML_TYPE_I64 | Llama.Internal.Types.Params |
| GGML_TYPE_I8 | Llama.Internal.Types.Params |
| GGML_TYPE_IQ1_M | Llama.Internal.Types.Params |
| GGML_TYPE_IQ1_S | Llama.Internal.Types.Params |
| GGML_TYPE_IQ2_S | Llama.Internal.Types.Params |
| GGML_TYPE_IQ2_XS | Llama.Internal.Types.Params |
| GGML_TYPE_IQ2_XXS | Llama.Internal.Types.Params |
| GGML_TYPE_IQ3_S | Llama.Internal.Types.Params |
| GGML_TYPE_IQ3_XXS | Llama.Internal.Types.Params |
| GGML_TYPE_IQ4_NL | Llama.Internal.Types.Params |
| GGML_TYPE_IQ4_XS | Llama.Internal.Types.Params |
| GGML_TYPE_Q2_K | Llama.Internal.Types.Params |
| GGML_TYPE_Q3_K | Llama.Internal.Types.Params |
| GGML_TYPE_Q4_0 | Llama.Internal.Types.Params |
| GGML_TYPE_Q4_1 | Llama.Internal.Types.Params |
| GGML_TYPE_Q4_K | Llama.Internal.Types.Params |
| GGML_TYPE_Q5_0 | Llama.Internal.Types.Params |
| GGML_TYPE_Q5_1 | Llama.Internal.Types.Params |
| GGML_TYPE_Q5_K | Llama.Internal.Types.Params |
| GGML_TYPE_Q6_K | Llama.Internal.Types.Params |
| GGML_TYPE_Q8_0 | Llama.Internal.Types.Params |
| GGML_TYPE_Q8_1 | Llama.Internal.Types.Params |
| GGML_TYPE_Q8_K | Llama.Internal.Types.Params |
| GGML_TYPE_TQ1_0 | Llama.Internal.Types.Params |
| GGML_TYPE_TQ2_0 | Llama.Internal.Types.Params |
| id | Llama.Internal.Types |
| iface | Llama.Internal.Types |
| imatrix | Llama.Internal.Types.Params |
| initAdapterLora | Llama.Adapter |
| initContextFromModel | Llama.Model |
| initDistributedSampler | Llama.Sampler |
| initDrySampler | Llama.Sampler |
| initGrammarLazyPatternsSampler | Llama.Sampler |
| initGrammarSampler | Llama.Sampler |
| initGreedySampler | Llama.Sampler |
| initInfillSampler | Llama.Sampler |
| initLogitBiasSampler | Llama.Sampler |
| initMinPSampler | Llama.Sampler |
| initMirostatSampler | Llama.Sampler |
| initMirostatV2Sampler | Llama.Sampler |
| initPenaltiesSampler | Llama.Sampler |
| initSampler | Llama.Sampler |
| initSamplerChain | Llama.Sampler |
| initTempExtSampler | Llama.Sampler |
| initTempSampler | Llama.Sampler |
| initTopKSampler | Llama.Sampler |
| initTopNSigmaSampler | Llama.Sampler |
| initTopPSampler | Llama.Sampler |
| initTypicalSampler | Llama.Sampler |
| initXTCSampler | Llama.Sampler |
| isVocabTokenControl | Llama.Vocab |
| isVocabTokenEog | Llama.Vocab |
| keepSplit | Llama.Internal.Types.Params |
| KVCache | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| kvCacheViewInit | Llama.KVCache |
| kvCacheViewUpdate | Llama.KVCache |
| kvOverrides | Llama.Internal.Types.Params |
| kvOverridesQuantizeParams | Llama.Internal.Types.Params |
| kvSelfCanShift | Llama.KVCache |
| kvSelfClear | Llama.KVCache |
| kvSelfDefrag | Llama.KVCache |
| kvSelfNumTokens | Llama.KVCache |
| kvSelfSeqAdd | Llama.KVCache |
| kvSelfSeqCopy | Llama.KVCache |
| kvSelfSeqDiv | Llama.KVCache |
| kvSelfSeqKeep | Llama.KVCache |
| kvSelfSeqPosMax | Llama.KVCache |
| kvSelfSeqRemove | Llama.KVCache |
| kvSelfUpdate | Llama.KVCache |
| kvSelfUsedCells | Llama.KVCache |
| LlamaAttentionType | Llama.Internal.Types.Params |
| llamaBackendFree | Llama.Backend |
| llamaBackendInit | Llama.Backend |
| LlamaBatch | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaChatMessage | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaContextParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| LlamaKvCacheView | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaLogitBias | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaModelParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| LlamaModelQuantizeParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| LlamaPerfContextData | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaPerfSamplerData | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaPoolingType | Llama.Internal.Types.Params |
| LlamaPos | Llama.Internal.Types |
| LlamaRopeTypeScaling | Llama.Internal.Types.Params |
| LlamaSampler | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaSamplerChainParams | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| LlamaSamplerContext | Llama.Internal.Types |
| LlamaSamplerI | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaSeqId | Llama.Internal.Types |
| LlamaSplitMode | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| LlamaToken | Llama.Internal.Types |
| LlamaTokenData | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaTokenDataArray | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| LlamaVocabType | Llama.Internal.Types.Params |
| LLAMA_ATTENTION_TYPE_CAUSAL | Llama.Internal.Types.Params |
| LLAMA_ATTENTION_TYPE_NON_CAUSAL | Llama.Internal.Types.Params |
| LLAMA_ATTENTION_TYPE_UNSPECIFIED | Llama.Internal.Types.Params |
| llama_max_devices | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_n_batch | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_n_ctx | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_n_seq_max | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_n_ubatch | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| LLAMA_POOLING_TYPE_CLS | Llama.Internal.Types.Params |
| LLAMA_POOLING_TYPE_LAST | Llama.Internal.Types.Params |
| LLAMA_POOLING_TYPE_MEAN | Llama.Internal.Types.Params |
| LLAMA_POOLING_TYPE_NONE | Llama.Internal.Types.Params |
| LLAMA_POOLING_TYPE_RANK | Llama.Internal.Types.Params |
| LLAMA_POOLING_TYPE_UNSPECIFIED | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_LINEAR | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_LONGROPE | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_MAX_VALUE | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_NONE | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED | Llama.Internal.Types.Params |
| LLAMA_ROPE_SCALING_TYPE_YARN | Llama.Internal.Types.Params |
| llama_supports_gpu_offload | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_supports_mlock | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_supports_mmap | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_supports_rpc | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| llama_time_us | Llama.Internal.Foreign.Context, Llama.Internal.Foreign |
| LLAMA_VOCAB_TYPE_BPE | Llama.Internal.Types.Params |
| LLAMA_VOCAB_TYPE_NONE | Llama.Internal.Types.Params |
| LLAMA_VOCAB_TYPE_RWKV | Llama.Internal.Types.Params |
| LLAMA_VOCAB_TYPE_SPM | Llama.Internal.Types.Params |
| LLAMA_VOCAB_TYPE_UGM | Llama.Internal.Types.Params |
| LLAMA_VOCAB_TYPE_WPM | Llama.Internal.Types.Params |
| loadModelFromFile | Llama.Model |
| loadModelFromSplits | Llama.Model |
| loadSequenceStateFromFile | Llama.State |
| loadStateFromFile | Llama.State |
| logit | Llama.Internal.Types |
| logits | Llama.Internal.Types |
| logits_all | Llama.Internal.Types.Params |
| mainGpu | Llama.Internal.Types.Params |
| max_contiguous | Llama.Internal.Types |
| max_contiguous_idx | Llama.Internal.Types |
| Model | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| ModelParamsPtr | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| ModelQuantizeParamsPtr | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| name | Llama.Internal.Types |
| Never | Llama.Internal.Types |
| nGpuLayers | Llama.Internal.Types.Params |
| noPerf | Llama.Internal.Types.Params |
| no_perf | Llama.Internal.Types.Params |
| nthread | Llama.Internal.Types.Params |
| n_batch | Llama.Internal.Types.Params |
| n_cells | Llama.Internal.Types |
| n_ctx | Llama.Internal.Types.Params |
| n_eval | Llama.Internal.Types |
| n_p_eval | Llama.Internal.Types |
| n_sample | Llama.Internal.Types |
| n_seq_id | Llama.Internal.Types |
| n_seq_max | |
| 1 (Function) | Llama.Internal.Types |
| 2 (Function) | Llama.Internal.Types.Params |
| n_threads | Llama.Internal.Types.Params |
| n_threads_batch | Llama.Internal.Types.Params |
| n_tokens | Llama.Internal.Types |
| n_ubatch | Llama.Internal.Types.Params |
| offload_kqv | Llama.Internal.Types.Params |
| onlyCopy | Llama.Internal.Types.Params |
| outputTensorType | Llama.Internal.Types.Params |
| p | Llama.Internal.Types |
| pooling_type | Llama.Internal.Types.Params |
| pos | Llama.Internal.Types |
| printContextPerformance | Llama.Performance |
| printSamplerPerformance | Llama.Performance |
| printSystemInfo | Llama.Split |
| progressCallback | Llama.Internal.Types.Params |
| progressCallbackUserData | Llama.Internal.Types.Params |
| pure_ | Llama.Internal.Types.Params |
| p_llama_adapter_lora_free | Llama.Internal.Foreign.Adapter, Llama.Internal.Foreign |
| p_llama_free | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| p_llama_model_free | Llama.Internal.Foreign.Model, Llama.Internal.Foreign |
| p_llama_sampler_free | Llama.Internal.Foreign.Sampler, Llama.Internal.Foreign |
| quantizeModel | Llama.Model |
| quantizeModelDefault | Llama.Model |
| quantizeOutputTensor | Llama.Internal.Types.Params |
| removeSamplerFromChain | Llama.Sampler |
| reset | Llama.Internal.Types |
| resetContextPerformance | Llama.Performance |
| resetSampler | Llama.Sampler |
| resetSamplerPerformance | Llama.Performance |
| rmAdapterLora | Llama.Adapter |
| role | Llama.Internal.Types |
| rope_freq_base | Llama.Internal.Types.Params |
| rope_freq_scale | Llama.Internal.Types.Params |
| rope_scaling_type | Llama.Internal.Types.Params |
| Sampler | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| SamplerChainParamsPtr | |
| 1 (Type/Class) | Llama.Internal.Types.Params |
| 2 (Data Constructor) | Llama.Internal.Types.Params |
| sampleWithSampler | Llama.Sampler |
| saveSequenceStateToFile | Llama.State |
| saveStateToFile | Llama.State |
| selected | Llama.Internal.Types |
| seq_id | Llama.Internal.Types |
| setAdapterLora | Llama.Adapter |
| setCausalAttention | Llama.Decode |
| setEmbeddingsEnabled | Llama.Decode |
| setSequenceStateData | Llama.State |
| setStateData | Llama.State |
| setThreadCount | Llama.Decode |
| setThreadCounts | Llama.Decode |
| setWarmupMode | Llama.Decode |
| size_ | Llama.Internal.Types |
| sorted | Llama.Internal.Types |
| splitMode | Llama.Internal.Types.Params |
| splitPath | Llama.Split |
| splitPrefix | Llama.Split |
| supportsGpuOffload | Llama.Context |
| supportsMLock | Llama.Context |
| supportsMMap | Llama.Context |
| supportsRpc | Llama.Context |
| synchronizeContext | Llama.Decode |
| tensorBuftOverrides | Llama.Internal.Types.Params |
| tensorSplit | Llama.Internal.Types.Params |
| tensorTypes | Llama.Internal.Types.Params |
| toCLlamaChatMessage | Llama.ChatTemplate |
| token | Llama.Internal.Types |
| tokenEmbeddingType | Llama.Internal.Types.Params |
| tokenize | Llama.Tokenize |
| tokenLogitBias | Llama.Internal.Types |
| tokenToPiece | Llama.Tokenize |
| token_count | Llama.Internal.Types |
| type_k | Llama.Internal.Types.Params |
| type_v | Llama.Internal.Types.Params |
| t_eval_ms | Llama.Internal.Types |
| t_load_ms | Llama.Internal.Types |
| t_p_eval_ms | Llama.Internal.Types |
| t_sample_ms | Llama.Internal.Types |
| t_start_ms | Llama.Internal.Types |
| used_cells | Llama.Internal.Types |
| useMlock | Llama.Internal.Types.Params |
| useMmap | Llama.Internal.Types.Params |
| Vocab | |
| 1 (Type/Class) | Llama.Internal.Types |
| 2 (Data Constructor) | Llama.Internal.Types |
| vocabOnly | Llama.Internal.Types.Params |
| yarn_attn_factor | Llama.Internal.Types.Params |
| yarn_beta_fast | Llama.Internal.Types.Params |
| yarn_beta_slow | Llama.Internal.Types.Params |
| yarn_ext_factor | Llama.Internal.Types.Params |
| yarn_orig_ctx | Llama.Internal.Types.Params |