aub_ai_bindings_generated library

Classes

AubAiBindings: Bindings for src/aub_ai.h.
ggml_backend_buffer
ggml_backend_type
ggml_log_level
ggml_op: available tensor operations:
ggml_tensor: n-dimensional tensor
ggml_type
llama_batch: Input data for llama_decode A llama_batch object can contain input about one or many sequences The provided arrays (i.e. token, embd, pos, etc.) must have size of n_tokens
llama_beam_view: Beam search
llama_beams_state: Passed to beam_search_callback function. Whenever 0 < common_prefix_length, this number of tokens should be copied from any of the beams (e.g. beams0) as they will be removed (shifted) from all beams in all subsequent callbacks. These pointers are valid only during the synchronous callback, so should not be saved.
llama_context
llama_context_params
llama_ftype: model file types
llama_grammar: grammar types
llama_grammar_element
llama_gretype: grammar element type
llama_kv_cache_view: An updateable view of the KV cache.
llama_kv_cache_view_cell: Information associated with an individual cell in the KV cache view.
llama_model: C interface
llama_model_params
llama_model_quantize_params: model quantization parameters
llama_rope_scaling_type
llama_timings: performance timing information
llama_token_data
llama_token_data_array
llama_token_type
llama_vocab_type

Dart__int64_t = int
Dartggml_log_callbackFunction = void Function(int level, Pointer<Char> text, Pointer<Void> user_data)
Dartllama_beam_search_callback_fn_tFunction = void Function(Pointer<Void>, llama_beams_state)
Dartllama_pos = int
Dartllama_progress_callbackFunction = void Function(double progress, Pointer<Void> ctx)
Dartllama_seq_id = int
Dartllama_token = int
FILE = __sFILE: stdio state variables.
fpos_t = __darwin_off_t
ggml_log_callback = Pointer<NativeFunction<ggml_log_callbackFunction>>
ggml_log_callbackFunction = Void Function(Int32 level, Pointer<Char> text, Pointer<Void> user_data)
llama_beam_search_callback_fn_t = Pointer<NativeFunction<llama_beam_search_callback_fn_tFunction>>: Type of pointer to the beam_search_callback function. void* callback_data is any custom data passed to llama_beam_search, that is subsequently passed back to beam_search_callback. This avoids having to use global variables in the callback.
llama_beam_search_callback_fn_tFunction = Void Function(Pointer<Void>, llama_beams_state)
llama_pos = Int32
llama_progress_callback = Pointer<NativeFunction<llama_progress_callbackFunction>>
llama_progress_callbackFunction = Void Function(Float progress, Pointer<Void> ctx)
llama_seq_id = Int32
llama_token = Int32