Skip to main content

Crate ik_llama_cpp_sys

Crate ik_llama_cpp_sys

Expand description

Low-level FFI bindings to ik_llama.cpp (ikawrakow’s SOTA-quant fork of llama.cpp).

The bindings are generated by bindgen in build.rs against the vendored ik_llama.cpp/include/llama.h + ggml/include/gguf.h and included below.

Structs§

Constants§

Functions§

ggml_abort^⚠
ggml_abs^⚠
ggml_abs_inplace^⚠
ggml_acc^⚠
ggml_acc_inplace^⚠
ggml_add^⚠
ggml_add1^⚠
ggml_add1_inplace^⚠
ggml_add_cast^⚠
ggml_add_id^⚠
ggml_add_inplace^⚠
ggml_add_rel_pos^⚠
ggml_add_rel_pos_inplace^⚠
ggml_arange^⚠
ggml_are_same_shape^⚠
ggml_are_same_stride^⚠
ggml_argmax^⚠
ggml_argsort^⚠
ggml_argsort_thresh^⚠
ggml_backend_alloc_buffer^⚠
ggml_backend_alloc_ctx_tensors^⚠
ggml_backend_alloc_ctx_tensors_from_buft^⚠
ggml_backend_buffer_clear^⚠
ggml_backend_buffer_free^⚠
ggml_backend_buffer_get_alignment^⚠
ggml_backend_buffer_get_alloc_size^⚠
ggml_backend_buffer_get_base^⚠
ggml_backend_buffer_get_max_size^⚠
ggml_backend_buffer_get_size^⚠
ggml_backend_buffer_get_type^⚠
ggml_backend_buffer_get_usage^⚠
ggml_backend_buffer_init_tensor^⚠
ggml_backend_buffer_is_host^⚠
ggml_backend_buffer_name^⚠
ggml_backend_buffer_reset^⚠
ggml_backend_buffer_set_usage^⚠
ggml_backend_buft_alloc_buffer^⚠
ggml_backend_buft_get_alignment^⚠
ggml_backend_buft_get_alloc_size^⚠
ggml_backend_buft_get_max_size^⚠
ggml_backend_buft_is_host^⚠
ggml_backend_buft_name^⚠
ggml_backend_compare_graph_backend^⚠
ggml_backend_cpu_buffer_from_ptr^⚠
ggml_backend_cpu_buffer_type^⚠
ggml_backend_cpu_init^⚠
ggml_backend_cpu_set_abort_callback^⚠
ggml_backend_cpu_set_moe_expert_prefetch^⚠
ggml_backend_cpu_set_n_threads^⚠
ggml_backend_event_free^⚠
ggml_backend_event_new^⚠
ggml_backend_event_record^⚠
ggml_backend_event_synchronize^⚠
ggml_backend_event_wait^⚠
ggml_backend_free^⚠
ggml_backend_get_alignment^⚠
ggml_backend_get_default_buffer_type^⚠
ggml_backend_get_max_size^⚠
ggml_backend_graph_compute^⚠
ggml_backend_graph_compute_async^⚠
ggml_backend_graph_copy^⚠
ggml_backend_graph_copy_free^⚠
ggml_backend_graph_plan_compute^⚠
ggml_backend_graph_plan_create^⚠
ggml_backend_graph_plan_free^⚠
ggml_backend_guid^⚠
ggml_backend_is_cpu^⚠
ggml_backend_name^⚠
ggml_backend_offload_op^⚠
ggml_backend_prefetch_init^⚠
ggml_backend_prefetch_register_mapping^⚠
ggml_backend_prefetch_unregister_mapping^⚠
ggml_backend_reg_alloc_buffer^⚠
ggml_backend_reg_find_by_name^⚠
ggml_backend_reg_get_count^⚠
ggml_backend_reg_get_default_buffer_type^⚠
ggml_backend_reg_get_name^⚠
ggml_backend_reg_init_backend^⚠
ggml_backend_reg_init_backend_from_str^⚠
ggml_backend_sched_alloc_graph^⚠
ggml_backend_sched_free^⚠
ggml_backend_sched_get_backend^⚠
ggml_backend_sched_get_backend_idx^⚠
ggml_backend_sched_get_buffer_size^⚠
ggml_backend_sched_get_n_backends^⚠
ggml_backend_sched_get_n_copies^⚠
ggml_backend_sched_get_n_splits^⚠
ggml_backend_sched_get_tensor_backend^⚠
ggml_backend_sched_graph_compute^⚠
ggml_backend_sched_graph_compute_async^⚠
ggml_backend_sched_new^⚠
ggml_backend_sched_reserve^⚠
ggml_backend_sched_reset^⚠
ggml_backend_sched_set_eval_callback^⚠
ggml_backend_sched_set_max_extra_alloc^⚠
ggml_backend_sched_set_only_active_experts^⚠
ggml_backend_sched_set_op_offload^⚠
ggml_backend_sched_set_split_mode_graph^⚠
ggml_backend_sched_set_tensor_backend^⚠
ggml_backend_sched_synchronize^⚠
ggml_backend_supports_buft^⚠
ggml_backend_supports_op^⚠
ggml_backend_synchronize^⚠
ggml_backend_tensor_alloc^⚠
ggml_backend_tensor_copy^⚠
ggml_backend_tensor_copy_async^⚠
ggml_backend_tensor_get^⚠
ggml_backend_tensor_get_async^⚠
ggml_backend_tensor_set^⚠
ggml_backend_tensor_set_async^⚠
ggml_backend_view_init^⚠
ggml_bf16_to_fp32^⚠
ggml_bf16_to_fp32_row^⚠
ggml_blck_size^⚠
ggml_blend^⚠
ggml_build_backward_expand^⚠
ggml_build_backward_gradient_checkpointing^⚠
ggml_build_forward_expand^⚠
ggml_can_repeat^⚠
ggml_cast^⚠
ggml_clamp^⚠
ggml_concat^⚠
ggml_concat_inplace^⚠
ggml_cont^⚠
ggml_cont_1d^⚠
ggml_cont_2d^⚠
ggml_cont_3d^⚠
ggml_cont_4d^⚠
ggml_conv_1d^⚠
ggml_conv_1d_ph^⚠
ggml_conv_2d^⚠
ggml_conv_2d_dw^⚠
ggml_conv_2d_dw_direct^⚠
ggml_conv_2d_s1_ph^⚠
ggml_conv_2d_sk_p0^⚠
ggml_conv_depthwise_2d^⚠
ggml_conv_transpose_1d^⚠
ggml_conv_transpose_2d_p0^⚠
ggml_cpu_has_arm_fma^⚠
ggml_cpu_has_avx^⚠
ggml_cpu_has_avx2^⚠
ggml_cpu_has_avx512^⚠
ggml_cpu_has_avx512_bf16^⚠
ggml_cpu_has_avx512_vbmi^⚠
ggml_cpu_has_avx512_vnni^⚠
ggml_cpu_has_avx_vnni^⚠
ggml_cpu_has_blas^⚠
ggml_cpu_has_cann^⚠
ggml_cpu_has_cuda^⚠
ggml_cpu_has_f16c^⚠
ggml_cpu_has_fma^⚠
ggml_cpu_has_fp16_va^⚠
ggml_cpu_has_gpublas^⚠
ggml_cpu_has_matmul_int8^⚠
ggml_cpu_has_metal^⚠
ggml_cpu_has_neon^⚠
ggml_cpu_has_rpc^⚠
ggml_cpu_has_sse3^⚠
ggml_cpu_has_ssse3^⚠
ggml_cpu_has_sve^⚠
ggml_cpu_has_sycl^⚠
ggml_cpu_has_vsx^⚠
ggml_cpu_has_vulkan^⚠
ggml_cpu_has_wasm_simd^⚠
ggml_cpy^⚠
ggml_cross_entropy_loss^⚠
ggml_cross_entropy_loss_back^⚠
ggml_cumsum^⚠
ggml_cycles^⚠
ggml_cycles_per_ms^⚠
ggml_delta_net^⚠
ggml_diag^⚠
ggml_diag_mask_inf^⚠
ggml_diag_mask_inf_inplace^⚠
ggml_diag_mask_zero^⚠
ggml_diag_mask_zero_inplace^⚠
ggml_div^⚠
ggml_div_inplace^⚠
ggml_dup^⚠
ggml_dup_inplace^⚠
ggml_dup_tensor^⚠
ggml_element_size^⚠
ggml_elu^⚠
ggml_elu_inplace^⚠
ggml_exp^⚠
ggml_exp_inplace^⚠
ggml_fake_cpy^⚠
ggml_fill^⚠
ggml_fill_inplace^⚠
ggml_flash_attn_back^⚠
ggml_flash_attn_ext^⚠
ggml_flash_attn_ext_add_sinks^⚠
ggml_flash_attn_ext_set_prec^⚠
ggml_fopen^⚠
ggml_format_name^⚠
ggml_fp16_to_fp32^⚠
ggml_fp16_to_fp32_row^⚠
ggml_fp32_to_bf16^⚠
ggml_fp32_to_bf16_row^⚠
ggml_fp32_to_bf16_row_ref^⚠
ggml_fp32_to_fp16^⚠
ggml_fp32_to_fp16_row^⚠
ggml_free^⚠
ggml_ftype_to_ggml_type^⚠
ggml_fused_mul_unary^⚠
ggml_fused_mul_unary_inplace^⚠
ggml_fused_norm^⚠
ggml_fused_norm_inplace^⚠
ggml_fused_rms_norm^⚠
ggml_fused_rms_norm_inplace^⚠
ggml_fused_rms_rms_add^⚠
ggml_fused_up_gate^⚠
ggml_gallocr_alloc_graph^⚠
ggml_gallocr_free^⚠
ggml_gallocr_get_buffer_size^⚠
ggml_gallocr_new^⚠
ggml_gallocr_new_n^⚠
ggml_gallocr_reserve^⚠
ggml_gallocr_reserve_n^⚠
ggml_geglu^⚠
ggml_geglu_erf^⚠
ggml_geglu_erf_split^⚠
ggml_geglu_erf_swapped^⚠
ggml_geglu_quick^⚠
ggml_geglu_quick_split^⚠
ggml_geglu_quick_swapped^⚠
ggml_geglu_split^⚠
ggml_geglu_swapped^⚠
ggml_gelu^⚠
ggml_gelu_erf^⚠
ggml_gelu_erf_inplace^⚠
ggml_gelu_inplace^⚠
ggml_gelu_quick^⚠
ggml_gelu_quick_inplace^⚠
ggml_get_data^⚠
ggml_get_data_f32^⚠
ggml_get_f32_1d^⚠
ggml_get_f32_nd^⚠
ggml_get_first_tensor^⚠
ggml_get_glu_op^⚠
ggml_get_i32_1d^⚠
ggml_get_i32_nd^⚠
ggml_get_max_tensor_size^⚠
ggml_get_mem_buffer^⚠
ggml_get_mem_size^⚠
ggml_get_name^⚠
ggml_get_next_tensor^⚠
ggml_get_no_alloc^⚠
ggml_get_rel_pos^⚠
ggml_get_rows^⚠
ggml_get_rows_back^⚠
ggml_get_tensor^⚠
ggml_get_unary_op^⚠
ggml_glu^⚠
ggml_glu_op_name^⚠
ggml_glu_split^⚠
ggml_graph_clear^⚠
ggml_graph_compute^⚠
ggml_graph_compute_with_ctx^⚠
ggml_graph_cpy^⚠
ggml_graph_dump_dot^⚠
ggml_graph_dup^⚠
ggml_graph_export^⚠
ggml_graph_get_tensor^⚠
ggml_graph_import^⚠
ggml_graph_n_nodes^⚠
ggml_graph_node^⚠
ggml_graph_nodes^⚠
ggml_graph_overhead^⚠
ggml_graph_overhead_custom^⚠
ggml_graph_plan^⚠
ggml_graph_print^⚠
ggml_graph_reset^⚠
ggml_graph_size^⚠
ggml_graph_view^⚠
ggml_group_norm^⚠
ggml_group_norm_inplace^⚠
ggml_grouped_topk^⚠
ggml_guid_matches^⚠
ggml_hadamard^⚠
ggml_hardsigmoid^⚠
ggml_hardswish^⚠
ggml_im2col^⚠
ggml_indexer_mask^⚠
ggml_indexer_topk^⚠
ggml_init^⚠
ggml_internal_get_type_traits^⚠
ggml_interpolate^⚠
ggml_is_3d^⚠
ggml_is_contiguous^⚠
ggml_is_contiguous_0^⚠
ggml_is_contiguous_1^⚠
ggml_is_contiguous_2^⚠
ggml_is_contiguous_channels^⚠
ggml_is_contiguous_rows^⚠
ggml_is_contiguously_allocated^⚠
ggml_is_empty^⚠
ggml_is_matrix^⚠
ggml_is_noop^⚠
ggml_is_numa^⚠
ggml_is_permuted^⚠
ggml_is_quantized^⚠
ggml_is_scalar^⚠
ggml_is_transposed^⚠
ggml_is_vector^⚠
ggml_l2_norm^⚠
ggml_l2_norm_inplace^⚠
ggml_leaky_relu^⚠
ggml_log^⚠
ggml_log_inplace^⚠
ggml_map_binary_f32^⚠
ggml_map_binary_inplace_f32^⚠
ggml_map_custom1^⚠
ggml_map_custom2^⚠
ggml_map_custom3^⚠
ggml_map_custom1_f32^⚠
ggml_map_custom1_inplace^⚠
ggml_map_custom1_inplace_f32^⚠
ggml_map_custom2_f32^⚠
ggml_map_custom2_inplace^⚠
ggml_map_custom2_inplace_f32^⚠
ggml_map_custom3_f32^⚠
ggml_map_custom3_inplace^⚠
ggml_map_custom3_inplace_f32^⚠
ggml_map_unary_f32^⚠
ggml_map_unary_inplace_f32^⚠
ggml_mean^⚠
ggml_moe_up_gate^⚠
ggml_moe_up_gate_ext^⚠
ggml_mul^⚠
ggml_mul_inplace^⚠
ggml_mul_mat^⚠
ggml_mul_mat_id^⚠
ggml_mul_mat_inplace^⚠
ggml_mul_mat_set_prec^⚠
ggml_mul_multi_add^⚠
ggml_multi_add^⚠
ggml_n_dims^⚠
ggml_nbytes^⚠
ggml_nbytes_pad^⚠
ggml_neg^⚠
ggml_neg_inplace^⚠
ggml_nelements^⚠
ggml_new_f32^⚠
ggml_new_graph^⚠
ggml_new_graph_custom^⚠
ggml_new_i32^⚠
ggml_new_tensor^⚠
ggml_new_tensor_1d^⚠
ggml_new_tensor_2d^⚠
ggml_new_tensor_3d^⚠
ggml_new_tensor_4d^⚠
ggml_norm^⚠
ggml_norm_inplace^⚠
ggml_nrows^⚠
ggml_numa_init^⚠
ggml_op_desc^⚠
ggml_op_name^⚠
ggml_op_symbol^⚠
ggml_opt^⚠
ggml_opt_default_params^⚠
ggml_opt_init^⚠
ggml_opt_resume^⚠
ggml_opt_resume_g^⚠
ggml_out_prod^⚠
ggml_pad^⚠
ggml_permute^⚠
ggml_pool_1d^⚠
ggml_pool_2d^⚠
ggml_print_object^⚠
ggml_print_objects^⚠
ggml_quantize_chunk^⚠
ggml_quantize_free^⚠
ggml_quantize_init^⚠
ggml_quantize_requires_imatrix^⚠
ggml_reduce^⚠
ggml_reglu^⚠
ggml_reglu_split^⚠
ggml_reglu_swapped^⚠
ggml_relu^⚠
ggml_relu_inplace^⚠
ggml_repeat^⚠
ggml_repeat_4d^⚠
ggml_repeat_back^⚠
ggml_reshape^⚠
ggml_reshape_1d^⚠
ggml_reshape_2d^⚠
ggml_reshape_3d^⚠
ggml_reshape_4d^⚠
ggml_reshape_4d_ext^⚠
ggml_rms_norm^⚠
ggml_rms_norm_back^⚠
ggml_rms_norm_inplace^⚠
ggml_rope^⚠
ggml_rope_back^⚠
ggml_rope_cache^⚠
ggml_rope_custom^⚠
ggml_rope_custom_inplace^⚠
ggml_rope_ext^⚠
ggml_rope_ext_inplace^⚠
ggml_rope_fast^⚠
ggml_rope_inplace^⚠
ggml_rope_multi^⚠
ggml_rope_multi_inplace^⚠
ggml_rope_yarn_corr_dims^⚠
ggml_row_size^⚠
ggml_scale^⚠
ggml_scale_bias^⚠
ggml_scale_bias_inplace^⚠
ggml_scale_inplace^⚠
ggml_set^⚠
ggml_set_1d^⚠
ggml_set_1d_inplace^⚠
ggml_set_2d^⚠
ggml_set_2d_inplace^⚠
ggml_set_f32^⚠
ggml_set_f32_1d^⚠
ggml_set_f32_nd^⚠
ggml_set_i32^⚠
ggml_set_i32_1d^⚠
ggml_set_i32_nd^⚠
ggml_set_inplace^⚠
ggml_set_input^⚠
ggml_set_name^⚠
ggml_set_no_alloc^⚠
ggml_set_output^⚠
ggml_set_param^⚠
ggml_set_rows^⚠
ggml_set_scratch^⚠
ggml_set_zero^⚠
ggml_sgn^⚠
ggml_sgn_inplace^⚠
ggml_sigmoid^⚠
ggml_sigmoid_inplace^⚠
ggml_silu^⚠
ggml_silu_back^⚠
ggml_silu_inplace^⚠
ggml_sinkhorn^⚠
ggml_soft_max^⚠
ggml_soft_max_add_sinks^⚠
ggml_soft_max_back^⚠
ggml_soft_max_back_inplace^⚠
ggml_soft_max_ext^⚠
ggml_soft_max_inplace^⚠
ggml_softcap^⚠
ggml_softcap_inplace^⚠
ggml_softcap_max^⚠
ggml_softcap_max_inplace^⚠
ggml_softplus^⚠
ggml_softplus_inplace^⚠
ggml_solve_tri^⚠
ggml_sqr^⚠
ggml_sqr_inplace^⚠
ggml_sqrt^⚠
ggml_sqrt_inplace^⚠
ggml_ssm_conv^⚠
ggml_ssm_scan^⚠
ggml_status_to_string^⚠
ggml_step^⚠
ggml_step_inplace^⚠
ggml_sub^⚠
ggml_sub_inplace^⚠
ggml_sum^⚠
ggml_sum_rows^⚠
ggml_sum_rows_ext^⚠
ggml_swiglu^⚠
ggml_swiglu_oai^⚠
ggml_swiglu_split^⚠
ggml_swiglu_swapped^⚠
ggml_tallocr_alloc^⚠
ggml_tallocr_new^⚠
ggml_tanh^⚠
ggml_tanh_inplace^⚠
ggml_tensor_overhead^⚠
ggml_time_init^⚠
ggml_time_ms^⚠
ggml_time_us^⚠
ggml_timestep_embedding^⚠
ggml_top_k^⚠
ggml_top_k_thresh^⚠
ggml_transpose^⚠
ggml_tri^⚠
ggml_type_name^⚠
ggml_type_size^⚠
ggml_type_sizef^⚠
ggml_unary^⚠
ggml_unary_inplace^⚠
ggml_unary_op_name^⚠
ggml_unravel_index^⚠
ggml_upscale^⚠
ggml_upscale_ext^⚠
ggml_used_mem^⚠
ggml_validate_row_data^⚠
ggml_view_1d^⚠
ggml_view_2d^⚠
ggml_view_3d^⚠
ggml_view_4d^⚠
ggml_view_tensor^⚠
ggml_win_part^⚠
ggml_win_unpart^⚠
gguf_add_tensor^⚠
gguf_find_key^⚠
gguf_find_tensor^⚠
gguf_free^⚠
gguf_get_alignment^⚠
gguf_get_arr_data^⚠
gguf_get_arr_n^⚠
gguf_get_arr_str^⚠
gguf_get_arr_type^⚠
gguf_get_data^⚠
gguf_get_data_offset^⚠
gguf_get_key^⚠
gguf_get_kv_type^⚠
gguf_get_meta_data^⚠
gguf_get_meta_size^⚠
gguf_get_n_kv^⚠
gguf_get_n_tensors^⚠
gguf_get_tensor_name^⚠
gguf_get_tensor_offset^⚠
gguf_get_tensor_type^⚠
gguf_get_val_bool^⚠
gguf_get_val_data^⚠
gguf_get_val_f32^⚠
gguf_get_val_f64^⚠
gguf_get_val_i8^⚠
gguf_get_val_i16^⚠
gguf_get_val_i32^⚠
gguf_get_val_i64^⚠
gguf_get_val_str^⚠
gguf_get_val_u8^⚠
gguf_get_val_u16^⚠
gguf_get_val_u32^⚠
gguf_get_val_u64^⚠
gguf_get_version^⚠
gguf_init_empty^⚠
gguf_init_from_file^⚠
gguf_remove_key^⚠
gguf_set_arr_data^⚠
gguf_set_arr_str^⚠
gguf_set_kv^⚠
gguf_set_tensor_data^⚠
gguf_set_tensor_type^⚠
gguf_set_val_bool^⚠
gguf_set_val_f32^⚠
gguf_set_val_f64^⚠
gguf_set_val_i8^⚠
gguf_set_val_i16^⚠
gguf_set_val_i32^⚠
gguf_set_val_i64^⚠
gguf_set_val_str^⚠
gguf_set_val_u8^⚠
gguf_set_val_u16^⚠
gguf_set_val_u32^⚠
gguf_set_val_u64^⚠
gguf_type_name^⚠
gguf_write_to_file^⚠
ik_llama_rs_grammar_accept^⚠
ik_llama_rs_grammar_apply^⚠
ik_llama_rs_json_schema_to_grammar^⚠
ik_llama_rs_mtp_begin^⚠
ik_llama_rs_mtp_free^⚠
ik_llama_rs_mtp_init^⚠
ik_llama_rs_mtp_step^⚠
ik_llama_rs_string_free^⚠
llama_add_bos_token^⚠
llama_add_eos_token^⚠
llama_backend_free^⚠
llama_backend_init^⚠
llama_batch_free^⚠
llama_batch_get_one^⚠
llama_batch_init^⚠
llama_chat_apply_template^⚠: Apply chat template. Inspired by hf apply_chat_template() on python. Both “model” and “custom_template” are optional, but at least one is required. “custom_template” has higher precedence than “model” NOTE: This function does not use a jinja parser. It only support a pre-defined list of template. See more: https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template @param tmpl A Jinja template to use for this chat. If this is nullptr, the model’s default chat template will be used instead. @param chat Pointer to a list of multiple llama_chat_message @param n_msg Number of llama_chat_message in this chat @param add_ass Whether to end the prompt with the token(s) that indicate the start of an assistant message. @param buf A buffer to hold the output formatted prompt. The recommended alloc size is 2 * (total number of characters of all messages) @param length The size of the allocated buffer @return The total number of bytes of the formatted prompt. If is it larger than the size of buffer, you may need to re-alloc it and then re-apply the template.
llama_chat_builtin_templates^⚠
llama_context_default_params^⚠
llama_control_vector_apply^⚠
llama_copy_state_data^⚠
llama_decode^⚠
llama_detokenize^⚠
llama_dump_timing_info_yaml^⚠
llama_encode^⚠
llama_fill_from_utf8^⚠
llama_free^⚠
llama_free_model^⚠
llama_get_dflash_draft_token_ith^⚠
llama_get_embeddings^⚠
llama_get_embeddings_ith^⚠
llama_get_embeddings_seq^⚠
llama_get_kv_cache_token_count^⚠
llama_get_kv_cache_used_cells^⚠
llama_get_logits^⚠
llama_get_logits_ith^⚠
llama_get_model^⚠
llama_get_model_tensor^⚠
llama_get_model_vocab^⚠
llama_get_state_size^⚠
llama_get_timings^⚠
llama_grammar_accept_token^⚠: @details Accepts the sampled token into the grammar
llama_grammar_apply^⚠: @details Apply constraints from grammar
llama_grammar_copy^⚠
llama_grammar_free^⚠
llama_grammar_init_lazy^⚠
llama_init_adaptive_p^⚠: @details Adaptive p sampler initializer @param target Select tokens near this probability (valid range 0.0 to 1.0; <0 = disabled) @param decay Decay rate for target adaptation over time. lower values -> faster but less stable adaptation. (valid range 0.0 to 1.0; ≤0 = no adaptation)
llama_init_from_model^⚠
llama_is_gemma4_mtp_file^⚠
llama_kv_cache_clear^⚠
llama_kv_cache_defrag^⚠
llama_kv_cache_seq_add^⚠
llama_kv_cache_seq_cp^⚠
llama_kv_cache_seq_div^⚠
llama_kv_cache_seq_keep^⚠
llama_kv_cache_seq_pos_max^⚠
llama_kv_cache_seq_pos_min^⚠
llama_kv_cache_seq_rm^⚠
llama_kv_cache_update^⚠
llama_kv_cache_view_free^⚠
llama_kv_cache_view_init^⚠
llama_kv_cache_view_update^⚠
llama_load_session_file^⚠
llama_log_set^⚠
llama_lora_adapter_clear^⚠
llama_lora_adapter_free^⚠
llama_lora_adapter_init^⚠
llama_lora_adapter_remove^⚠
llama_lora_adapter_set^⚠
llama_max_devices^⚠
llama_model_arch_string^⚠
llama_model_chat_template^⚠
llama_model_decoder_start_token^⚠
llama_model_default_params^⚠
llama_model_desc^⚠
llama_model_get_vocab^⚠
llama_model_has_decoder^⚠
llama_model_has_encoder^⚠
llama_model_has_recurrent^⚠
llama_model_is_gemma4_mtp_assistant^⚠
llama_model_is_hybrid^⚠
llama_model_is_openpangu^⚠
llama_model_is_recurrent^⚠
llama_model_is_split_mode_graph^⚠
llama_model_load_from_file^⚠
llama_model_meta_count^⚠
llama_model_meta_key_by_index^⚠
llama_model_meta_val_str^⚠
llama_model_meta_val_str_by_index^⚠
llama_model_n_embd^⚠
llama_model_n_embd_inp^⚠
llama_model_n_nextn_layer^⚠
llama_model_n_params^⚠
llama_model_quantize^⚠
llama_model_quantize_default_params^⚠
llama_model_size^⚠
llama_model_supports_ctx_shift^⚠
llama_model_supports_partial_kv_reuse^⚠
llama_n_batch^⚠
llama_n_ctx^⚠
llama_n_ctx_train^⚠
llama_n_layer^⚠
llama_n_seq_max^⚠
llama_n_threads^⚠
llama_n_threads_batch^⚠
llama_n_ubatch^⚠
llama_n_vocab^⚠
llama_numa_init^⚠
llama_pooling_type^⚠
llama_prep_adaptive_p^⚠
llama_print_system_info^⚠
llama_print_timings^⚠
llama_reload_changed_tensors^⚠
llama_reset_timings^⚠
llama_review_adaptive_p^⚠
llama_rope_freq_scale_train^⚠
llama_rope_type^⚠
llama_sample_adaptive_p^⚠: @details Adaptive p sampler described in https://github.com/MrJackSpade/adaptive-p-docs/blob/main/README.md
llama_sample_apply_guidance^⚠: @details Apply classifier-free guidance to the logits as described in academic paper “Stay on topic with Classifier-Free Guidance” https://arxiv.org/abs/2306.17806 @param logits Logits extracted from the original generation context. @param logits_guidance Logits extracted from a separate context from the same model. Other than a negative prompt at the beginning, it should have all generated and user input tokens copied from the main context. @param scale Guidance strength. 1.0f means no guidance. Higher values mean stronger guidance.
llama_sample_dist^⚠
llama_sample_dry^⚠
llama_sample_entropy^⚠: @details Dynamic temperature implementation described in the paper https://arxiv.org/abs/2309.02772.
llama_sample_grammar^⚠
llama_sample_min_p^⚠: @details Minimum P sampling as described in https://github.com/ggerganov/llama.cpp/pull/3841
llama_sample_repetition_penalties^⚠: @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix. @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details.
llama_sample_softmax^⚠: @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
llama_sample_tail_free^⚠: @details Tail Free Sampling described in https://www.trentonbricken.com/Tail-Free-Sampling/.
llama_sample_temp^⚠
llama_sample_token^⚠: @details Randomly selects a token from the candidates based on their probabilities using the RNG of ctx.
llama_sample_token_adaptive_p^⚠: @details Randonly selects a token from the candidates following adaptive p sampler.
llama_sample_token_greedy^⚠: @details Selects the token with the highest probability. Does not compute the token probabilities. Use llama_sample_softmax() instead.
llama_sample_token_mirostat^⚠: @details Mirostat 1.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words. @param candidates A vector of llama_token_data containing the candidate tokens, their probabilities (p), and log-odds (logit) for the current position in the generated text. @param tau The target cross-entropy (or surprise) value you want to achieve for the generated text. A higher value corresponds to more surprising or less predictable text, while a lower value corresponds to less surprising or more predictable text. @param eta The learning rate used to update mu based on the error between the target and observed surprisal of the sampled word. A larger learning rate will cause mu to be updated more quickly, while a smaller learning rate will result in slower updates. @param m The number of tokens considered in the estimation of s_hat. This is an arbitrary value that is used to calculate s_hat, which in turn helps to calculate the value of k. In the paper, they use m = 100, but you can experiment with different values to see how it affects the performance of the algorithm. @param mu Maximum cross-entropy. This value is initialized to be twice the target cross-entropy (2 * tau) and is updated in the algorithm based on the error between the target and observed surprisal.
llama_sample_token_mirostat_v2^⚠: @details Mirostat 2.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words. @param candidates A vector of llama_token_data containing the candidate tokens, their probabilities (p), and log-odds (logit) for the current position in the generated text. @param tau The target cross-entropy (or surprise) value you want to achieve for the generated text. A higher value corresponds to more surprising or less predictable text, while a lower value corresponds to less surprising or more predictable text. @param eta The learning rate used to update mu based on the error between the target and observed surprisal of the sampled word. A larger learning rate will cause mu to be updated more quickly, while a smaller learning rate will result in slower updates. @param mu Maximum cross-entropy. This value is initialized to be twice the target cross-entropy (2 * tau) and is updated in the algorithm based on the error between the target and observed surprisal.
llama_sample_top_k^⚠: @details Top-K sampling described in academic paper “The Curious Case of Neural Text Degeneration” https://arxiv.org/abs/1904.09751
llama_sample_top_n_sigma^⚠: @details Top n sigma sampling as described in academic paper “Top-nσ: Not All Logits Are You Need” https://arxiv.org/pdf/2411.07641
llama_sample_top_p^⚠: @details Nucleus sampling described in academic paper “The Curious Case of Neural Text Degeneration” https://arxiv.org/abs/1904.09751
llama_sample_typical^⚠: @details Locally Typical Sampling implementation described in the paper https://arxiv.org/abs/2202.00666.
llama_sample_xtc^⚠: @details XTC sampler as described in https://github.com/oobabooga/text-generation-webui/pull/6335
llama_sampler_dry_accept^⚠
llama_sampler_dry_clone^⚠
llama_sampler_dry_free^⚠
llama_sampler_dry_reset^⚠
llama_sampler_init_dry^⚠: @details DRY sampler, designed by p-e-w, as described in: https://github.com/oobabooga/text-generation-webui/pull/5677, porting Koboldcpp implementation authored by pi6am: https://github.com/LostRuins/koboldcpp/pull/982
llama_sampler_init_grammar^⚠: @details Intializes a GBNF grammar, see grammars/README.md for details. @param vocab The vocabulary that this grammar will be used with. @param grammar_str The production rules for the grammar, encoded as a string. Returns an empty grammar if empty. Returns NULL if parsing of grammar_str fails. @param grammar_root The name of the start symbol for the grammar.
llama_sampler_init_grammar_lazy^⚠: @details Lazy grammar sampler, introduced in https://github.com/ggerganov/llama.cpp/pull/9639 @param trigger_words A list of words that will trigger the grammar sampler. This may be updated to a loose regex syntax (w/ ^) in a near future. @param trigger_tokens A list of tokens that will trigger the grammar sampler.
llama_sampler_init_grammar_lazy_patterns^⚠: @details Lazy grammar sampler, introduced in https://github.com/ggml-org/llama.cpp/pull/9639 @param trigger_patterns A list of patterns that will trigger the grammar sampler. Pattern will be matched from the start of the generation output, and grammar sampler will be fed content starting from its first match group. @param trigger_tokens A list of tokens that will trigger the grammar sampler. Grammar sampler will be fed content starting from the trigger token included.
llama_sampler_reset^⚠
llama_save_session_file^⚠
llama_set_abort_callback^⚠
llama_set_causal_attn^⚠
llama_set_draft_input_hidden_state^⚠
llama_set_embeddings^⚠
llama_set_mtp_op_type^⚠
llama_set_n_threads^⚠
llama_set_offload_policy^⚠
llama_set_rng_seed^⚠
llama_set_state_data^⚠
llama_spec_ckpt_discard^⚠
llama_spec_ckpt_init^⚠
llama_spec_ckpt_restore^⚠
llama_spec_ckpt_save^⚠
llama_split_path^⚠: @details Build a split GGUF final path for this chunk. llama_split_path(split_path, sizeof(split_path), “/models/ggml-model-q4_0”, 2, 4) => split_path = “/models/ggml-model-q4_0-00002-of-00004.gguf”
llama_split_prefix^⚠: @details Extract the path prefix from the split_path if and only if the split_no and split_count match. llama_split_prefix(split_prefix, 64, “/models/ggml-model-q4_0-00002-of-00004.gguf”, 2, 4) => split_prefix = “/models/ggml-model-q4_0”
llama_state_get_data^⚠
llama_state_get_size^⚠
llama_state_load_file^⚠
llama_state_save_file^⚠
llama_state_seq_get_data^⚠
llama_state_seq_get_size^⚠
llama_state_seq_load_file^⚠
llama_state_seq_save_file^⚠
llama_state_seq_set_data^⚠
llama_state_set_data^⚠
llama_supports_gpu_offload^⚠
llama_supports_mlock^⚠
llama_supports_mmap^⚠
llama_synchronize^⚠
llama_time_us^⚠
llama_token_bos^⚠
llama_token_cls^⚠
llama_token_eos^⚠
llama_token_eot^⚠
llama_token_get_attr^⚠
llama_token_get_score^⚠
llama_token_get_text^⚠
llama_token_is_control^⚠
llama_token_is_eog^⚠
llama_token_middle^⚠
llama_token_nl^⚠
llama_token_pad^⚠
llama_token_prefix^⚠
llama_token_sep^⚠
llama_token_suffix^⚠
llama_token_to_piece^⚠
llama_token_to_piece_vocab^⚠
llama_tokenize^⚠: @details Convert the provided text into tokens. @param tokens The tokens pointer must be large enough to hold the resulting tokens. @return Returns the number of tokens on success, no more than n_tokens_max @return Returns a negative number on failure - the number of tokens that would have been returned @param add_special Allow to add BOS and EOS tokens if model is configured to do so. @param parse_special Allow tokenizing special and/or control tokens which otherwise are not exposed and treated as plaintext. Does not insert a leading space.
llama_vocab_bos^⚠
llama_vocab_eos^⚠
llama_vocab_get_add_bos^⚠
llama_vocab_get_add_eos^⚠
llama_vocab_get_text^⚠
llama_vocab_is_eog^⚠
llama_vocab_n_tokens^⚠
llama_vocab_tokenize^⚠
llama_vocab_type^⚠

Type Aliases§

Unions§

llama_model_kv_override__bindgen_ty_1