List of all items
Structs
- _IO_FILE
- _IO_codecvt
- _IO_marker
- _IO_wide_data
- ggml_backend
- ggml_backend_buffer
- ggml_backend_buffer_type
- ggml_backend_event
- ggml_backend_graph_copy
- ggml_backend_sched
- ggml_bf16_t
- ggml_cgraph
- ggml_context
- ggml_cplan
- ggml_gallocr
- ggml_hash_set
- ggml_init_params
- ggml_object
- ggml_opt_context
- ggml_opt_context__bindgen_ty_1
- ggml_opt_context__bindgen_ty_2
- ggml_opt_params
- ggml_opt_params__bindgen_ty_1
- ggml_opt_params__bindgen_ty_2
- ggml_scratch
- ggml_split_tensor_t
- ggml_tallocr
- ggml_tensor
- ggml_type_traits_t
- gguf_context
- gguf_init_params
- ik_llama_rs_mtp
- llama_batch
- llama_chat_message
- llama_context
- llama_context_params
- llama_grammar
- llama_kv_cache_view
- llama_kv_cache_view_cell
- llama_lora_adapter
- llama_model
- llama_model_kv_override
- llama_model_params
- llama_model_quantize_params
- llama_model_tensor_buft_override
- llama_sampler
- llama_sampler_adaptive_p
- llama_sampler_dry
- llama_sampler_grammar
- llama_sampler_i
- llama_timings
- llama_token_data
- llama_token_data_array
- llama_vocab
- quantize_user_data
Unions
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_custom1_f32
- ggml_map_custom1_inplace
- ggml_map_custom1_inplace_f32
- ggml_map_custom2
- ggml_map_custom2_f32
- ggml_map_custom2_inplace
- ggml_map_custom2_inplace_f32
- ggml_map_custom3
- 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_i16
- gguf_get_val_i32
- gguf_get_val_i64
- gguf_get_val_i8
- gguf_get_val_str
- gguf_get_val_u16
- gguf_get_val_u32
- gguf_get_val_u64
- gguf_get_val_u8
- 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_i16
- gguf_set_val_i32
- gguf_set_val_i64
- gguf_set_val_i8
- gguf_set_val_str
- gguf_set_val_u16
- gguf_set_val_u32
- gguf_set_val_u64
- gguf_set_val_u8
- 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
- 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
- llama_grammar_apply
- llama_grammar_copy
- llama_grammar_free
- llama_grammar_init_lazy
- llama_init_adaptive_p
- 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
- llama_sample_apply_guidance
- llama_sample_dist
- llama_sample_dry
- llama_sample_entropy
- llama_sample_grammar
- llama_sample_min_p
- llama_sample_repetition_penalties
- llama_sample_softmax
- llama_sample_tail_free
- llama_sample_temp
- llama_sample_token
- llama_sample_token_adaptive_p
- llama_sample_token_greedy
- llama_sample_token_mirostat
- llama_sample_token_mirostat_v2
- llama_sample_top_k
- llama_sample_top_n_sigma
- llama_sample_top_p
- llama_sample_typical
- llama_sample_xtc
- llama_sampler_dry_accept
- llama_sampler_dry_clone
- llama_sampler_dry_free
- llama_sampler_dry_reset
- llama_sampler_init_dry
- llama_sampler_init_grammar
- llama_sampler_init_grammar_lazy
- llama_sampler_init_grammar_lazy_patterns
- 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
- llama_split_prefix
- 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
- 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
- FILE
- _IO_lock_t
- __off64_t
- __off_t
- ggml_abort_callback
- ggml_backend_buffer_t
- ggml_backend_buffer_type_t
- ggml_backend_buffer_usage
- ggml_backend_eval_callback
- ggml_backend_event_t
- ggml_backend_graph_plan_t
- ggml_backend_sched_eval_callback
- ggml_backend_sched_t
- ggml_backend_t
- ggml_backend_type
- ggml_binary_op_f32_t
- ggml_bitset_t
- ggml_cgraph_eval_order
- ggml_custom1_op_f32_t
- ggml_custom1_op_t
- ggml_custom2_op_f32_t
- ggml_custom2_op_t
- ggml_custom3_op_f32_t
- ggml_custom3_op_t
- ggml_fp16_t
- ggml_from_float_t
- ggml_from_float_to_mat_t
- ggml_ftype
- ggml_gallocr_t
- ggml_gemm_t
- ggml_gemv_t
- ggml_glu_op
- ggml_guid
- ggml_guid_t
- ggml_linesearch
- ggml_log_callback
- ggml_log_level
- ggml_numa_strategy
- ggml_object_type
- ggml_op
- ggml_op_pool
- ggml_opt_callback
- ggml_opt_result
- ggml_opt_type
- ggml_prec
- ggml_scale_flag
- ggml_scale_mode
- ggml_sort_order
- ggml_status
- ggml_tensor_flag
- ggml_to_float_t
- ggml_tri_type
- ggml_type
- ggml_unary_op
- ggml_unary_op_f32_t
- ggml_vec_dot_t
- gguf_type
- llama_attention_type
- llama_flash_attn_type
- llama_ftype
- llama_model_kv_override_type
- llama_mtp_op_type
- llama_pooling_type
- llama_pos
- llama_progress_callback
- llama_rope_scaling_type
- llama_rope_type
- llama_rs_status
- llama_sampler_context_t
- llama_seq_id
- llama_spec_ckpt_mode
- llama_split_mode
- llama_state_seq_flags
- llama_token
- llama_token_attr
- llama_token_type
- llama_vocab_type
Constants
- GGML_BACKEND_BUFFER_USAGE_ANY
- GGML_BACKEND_BUFFER_USAGE_COMPUTE
- GGML_BACKEND_BUFFER_USAGE_WEIGHTS
- GGML_BACKEND_TYPE_CPU
- GGML_BACKEND_TYPE_GPU
- GGML_BACKEND_TYPE_GPU_SPLIT
- GGML_CGRAPH_EVAL_ORDER_COUNT
- GGML_CGRAPH_EVAL_ORDER_LEFT_TO_RIGHT
- GGML_CGRAPH_EVAL_ORDER_RIGHT_TO_LEFT
- GGML_FTYPE_ALL_F32
- GGML_FTYPE_MOSTLY_BF16
- GGML_FTYPE_MOSTLY_BF16_R16
- GGML_FTYPE_MOSTLY_F16
- GGML_FTYPE_MOSTLY_IQ1_BN
- GGML_FTYPE_MOSTLY_IQ1_KT
- GGML_FTYPE_MOSTLY_IQ1_M
- GGML_FTYPE_MOSTLY_IQ1_M_R4
- GGML_FTYPE_MOSTLY_IQ1_S
- GGML_FTYPE_MOSTLY_IQ1_S_R4
- GGML_FTYPE_MOSTLY_IQ2_BN
- GGML_FTYPE_MOSTLY_IQ2_BN_R4
- GGML_FTYPE_MOSTLY_IQ2_K
- GGML_FTYPE_MOSTLY_IQ2_KL
- GGML_FTYPE_MOSTLY_IQ2_KS
- GGML_FTYPE_MOSTLY_IQ2_KT
- GGML_FTYPE_MOSTLY_IQ2_K_R4
- GGML_FTYPE_MOSTLY_IQ2_S
- GGML_FTYPE_MOSTLY_IQ2_S_R4
- GGML_FTYPE_MOSTLY_IQ2_XS
- GGML_FTYPE_MOSTLY_IQ2_XS_R4
- GGML_FTYPE_MOSTLY_IQ2_XXS
- GGML_FTYPE_MOSTLY_IQ2_XXS_R4
- GGML_FTYPE_MOSTLY_IQ3_K
- GGML_FTYPE_MOSTLY_IQ3_KS
- GGML_FTYPE_MOSTLY_IQ3_KT
- GGML_FTYPE_MOSTLY_IQ3_K_R4
- GGML_FTYPE_MOSTLY_IQ3_S
- GGML_FTYPE_MOSTLY_IQ3_S_R4
- GGML_FTYPE_MOSTLY_IQ3_XXS
- GGML_FTYPE_MOSTLY_IQ3_XXS_R4
- GGML_FTYPE_MOSTLY_IQ4_K
- GGML_FTYPE_MOSTLY_IQ4_KS
- GGML_FTYPE_MOSTLY_IQ4_KSS
- GGML_FTYPE_MOSTLY_IQ4_KS_R4
- GGML_FTYPE_MOSTLY_IQ4_KT
- GGML_FTYPE_MOSTLY_IQ4_K_R4
- GGML_FTYPE_MOSTLY_IQ4_NL
- GGML_FTYPE_MOSTLY_IQ4_NL_R4
- GGML_FTYPE_MOSTLY_IQ4_XS
- GGML_FTYPE_MOSTLY_IQ4_XS_R8
- GGML_FTYPE_MOSTLY_IQ5_K
- GGML_FTYPE_MOSTLY_IQ5_KS
- GGML_FTYPE_MOSTLY_IQ5_KS_R4
- GGML_FTYPE_MOSTLY_IQ5_K_R4
- GGML_FTYPE_MOSTLY_IQ6_K
- GGML_FTYPE_MOSTLY_MXFP4
- GGML_FTYPE_MOSTLY_Q1_0_128
- GGML_FTYPE_MOSTLY_Q2_K
- GGML_FTYPE_MOSTLY_Q2_K_R4
- GGML_FTYPE_MOSTLY_Q3_K
- GGML_FTYPE_MOSTLY_Q3_K_R4
- GGML_FTYPE_MOSTLY_Q4_0
- GGML_FTYPE_MOSTLY_Q4_0_4_4
- GGML_FTYPE_MOSTLY_Q4_0_4_8
- GGML_FTYPE_MOSTLY_Q4_0_8_8
- GGML_FTYPE_MOSTLY_Q4_0_R8
- GGML_FTYPE_MOSTLY_Q4_1
- GGML_FTYPE_MOSTLY_Q4_1_SOME_F16
- GGML_FTYPE_MOSTLY_Q4_K
- GGML_FTYPE_MOSTLY_Q4_K_R4
- GGML_FTYPE_MOSTLY_Q5_0
- GGML_FTYPE_MOSTLY_Q5_0_R4
- GGML_FTYPE_MOSTLY_Q5_1
- GGML_FTYPE_MOSTLY_Q5_K
- GGML_FTYPE_MOSTLY_Q5_K_R4
- GGML_FTYPE_MOSTLY_Q6_0
- GGML_FTYPE_MOSTLY_Q6_0_R4
- GGML_FTYPE_MOSTLY_Q6_K
- GGML_FTYPE_MOSTLY_Q6_K_R4
- GGML_FTYPE_MOSTLY_Q8_0
- GGML_FTYPE_MOSTLY_Q8_0_R8
- GGML_FTYPE_MOSTLY_Q8_KV
- GGML_FTYPE_MOSTLY_Q8_KV_R8
- GGML_FTYPE_MOSTLY_Q8_K_R16
- GGML_FTYPE_MOSTLY_Q8_K_R8
- GGML_FTYPE_UNKNOWN
- GGML_GLU_OP_COUNT
- GGML_GLU_OP_GEGLU
- GGML_GLU_OP_GEGLU_ERF
- GGML_GLU_OP_GEGLU_QUICK
- GGML_GLU_OP_REGLU
- GGML_GLU_OP_SWIGLU
- GGML_GLU_OP_SWIGLU_OAI
- GGML_LINESEARCH_BACKTRACKING_ARMIJO
- GGML_LINESEARCH_BACKTRACKING_STRONG_WOLFE
- GGML_LINESEARCH_BACKTRACKING_WOLFE
- GGML_LINESEARCH_DEFAULT
- GGML_LINESEARCH_FAIL
- GGML_LINESEARCH_INVALID_PARAMETERS
- GGML_LINESEARCH_MAXIMUM_ITERATIONS
- GGML_LINESEARCH_MAXIMUM_STEP
- GGML_LINESEARCH_MINIMUM_STEP
- GGML_LOG_LEVEL_CONT
- GGML_LOG_LEVEL_DEBUG
- GGML_LOG_LEVEL_ERROR
- GGML_LOG_LEVEL_INFO
- GGML_LOG_LEVEL_NONE
- GGML_LOG_LEVEL_WARN
- GGML_NUMA_STRATEGY_COUNT
- GGML_NUMA_STRATEGY_DISABLED
- GGML_NUMA_STRATEGY_DISTRIBUTE
- GGML_NUMA_STRATEGY_ISOLATE
- GGML_NUMA_STRATEGY_MIRROR
- GGML_NUMA_STRATEGY_NUMACTL
- GGML_OBJECT_TYPE_GRAPH
- GGML_OBJECT_TYPE_TENSOR
- GGML_OBJECT_TYPE_WORK_BUFFER
- GGML_OPT_RESULT_CANCEL
- GGML_OPT_RESULT_DID_NOT_CONVERGE
- GGML_OPT_RESULT_FAIL
- GGML_OPT_RESULT_INVALID_WOLFE
- GGML_OPT_RESULT_NO_CONTEXT
- GGML_OPT_RESULT_OK
- GGML_OPT_TYPE_ADAM
- GGML_OPT_TYPE_LBFGS
- GGML_OP_ACC
- GGML_OP_ADD
- GGML_OP_ADD1
- GGML_OP_ADD_ID
- GGML_OP_ADD_REL_POS
- GGML_OP_ARANGE
- GGML_OP_ARGMAX
- GGML_OP_ARGSORT
- GGML_OP_ARGSORT_THRESH
- GGML_OP_BLEND
- GGML_OP_CLAMP
- GGML_OP_CONCAT
- GGML_OP_CONT
- GGML_OP_CONV_2D
- GGML_OP_CONV_2D_DW
- GGML_OP_CONV_TRANSPOSE_1D
- GGML_OP_CONV_TRANSPOSE_2D
- GGML_OP_COUNT
- GGML_OP_CPY
- GGML_OP_CROSS_ENTROPY_LOSS
- GGML_OP_CROSS_ENTROPY_LOSS_BACK
- GGML_OP_CUMSUM
- GGML_OP_DELTA_NET
- GGML_OP_DIAG
- GGML_OP_DIAG_MASK_INF
- GGML_OP_DIAG_MASK_ZERO
- GGML_OP_DIV
- GGML_OP_DUP
- GGML_OP_FAKE_CPY
- GGML_OP_FILL
- GGML_OP_FLASH_ATTN_BACK
- GGML_OP_FLASH_ATTN_EXT
- GGML_OP_FUSED_MUL_UNARY
- GGML_OP_FUSED_NORM
- GGML_OP_FUSED_RMS_NORM
- GGML_OP_FUSED_RMS_RMS_ADD
- GGML_OP_FUSED_UP_GATE
- GGML_OP_GET_REL_POS
- GGML_OP_GET_ROWS
- GGML_OP_GET_ROWS_BACK
- GGML_OP_GLU
- GGML_OP_GROUPED_TOPK
- GGML_OP_GROUP_NORM
- GGML_OP_HADAMARD
- GGML_OP_IM2COL
- GGML_OP_INDEXER_TOPK
- GGML_OP_L2_NORM
- GGML_OP_LEAKY_RELU
- GGML_OP_LOG
- GGML_OP_MAP_BINARY
- GGML_OP_MAP_CUSTOM1
- GGML_OP_MAP_CUSTOM1_F32
- GGML_OP_MAP_CUSTOM2
- GGML_OP_MAP_CUSTOM2_F32
- GGML_OP_MAP_CUSTOM3
- GGML_OP_MAP_CUSTOM3_F32
- GGML_OP_MAP_UNARY
- GGML_OP_MASK_TOPK
- GGML_OP_MEAN
- GGML_OP_MOE_FUSED_UP_GATE
- GGML_OP_MUL
- GGML_OP_MULTI_ADD
- GGML_OP_MUL_MAT
- GGML_OP_MUL_MAT_ID
- GGML_OP_MUL_MULTI_ADD
- GGML_OP_NONE
- GGML_OP_NORM
- GGML_OP_OUT_PROD
- GGML_OP_PAD
- GGML_OP_PERMUTE
- GGML_OP_POOL_1D
- GGML_OP_POOL_2D
- GGML_OP_POOL_AVG
- GGML_OP_POOL_COUNT
- GGML_OP_POOL_MAX
- GGML_OP_REDUCE
- GGML_OP_REPEAT
- GGML_OP_REPEAT_BACK
- GGML_OP_RESHAPE
- GGML_OP_RMS_NORM
- GGML_OP_RMS_NORM_BACK
- GGML_OP_ROPE
- GGML_OP_ROPE_BACK
- GGML_OP_ROPE_CACHE
- GGML_OP_ROPE_FAST
- GGML_OP_SCALE
- GGML_OP_SET
- GGML_OP_SET_ROWS
- GGML_OP_SILU_BACK
- GGML_OP_SINKHORN
- GGML_OP_SOFTCAP
- GGML_OP_SOFT_CAP_MAX
- GGML_OP_SOFT_MAX
- GGML_OP_SOFT_MAX_BACK
- GGML_OP_SOLVE_TRI
- GGML_OP_SQR
- GGML_OP_SQRT
- GGML_OP_SSM_CONV
- GGML_OP_SSM_SCAN
- GGML_OP_SUB
- GGML_OP_SUM
- GGML_OP_SUM_ROWS
- GGML_OP_TIMESTEP_EMBEDDING
- GGML_OP_TRANSPOSE
- GGML_OP_TRI
- GGML_OP_UNARY
- GGML_OP_UPSCALE
- GGML_OP_VIEW
- GGML_OP_WIN_PART
- GGML_OP_WIN_UNPART
- GGML_PREC_DEFAULT
- GGML_PREC_F32
- GGML_SCALE_FLAG_ALIGN_CORNERS
- GGML_SCALE_MODE_BICUBIC
- GGML_SCALE_MODE_BILINEAR
- GGML_SCALE_MODE_COUNT
- GGML_SCALE_MODE_NEAREST
- GGML_SORT_ORDER_ASC
- GGML_SORT_ORDER_DESC
- GGML_STATUS_ABORTED
- GGML_STATUS_ALLOC_FAILED
- GGML_STATUS_FAILED
- GGML_STATUS_SUCCESS
- GGML_TENSOR_FLAG_INPUT
- GGML_TENSOR_FLAG_LOSS
- GGML_TENSOR_FLAG_OUTPUT
- GGML_TENSOR_FLAG_PARAM
- GGML_TRI_TYPE_LOWER
- GGML_TRI_TYPE_LOWER_DIAG
- GGML_TRI_TYPE_UPPER
- GGML_TRI_TYPE_UPPER_DIAG
- GGML_TYPE_BF16
- GGML_TYPE_BF16_R16
- GGML_TYPE_COUNT
- GGML_TYPE_F16
- GGML_TYPE_F32
- GGML_TYPE_F64
- GGML_TYPE_I16
- GGML_TYPE_I2_S
- GGML_TYPE_I32
- GGML_TYPE_I64
- GGML_TYPE_I8
- GGML_TYPE_IQ1_BN
- GGML_TYPE_IQ1_KT
- GGML_TYPE_IQ1_M
- GGML_TYPE_IQ1_M_R4
- GGML_TYPE_IQ1_S
- GGML_TYPE_IQ1_S_R4
- GGML_TYPE_IQ2_BN
- GGML_TYPE_IQ2_BN_R4
- GGML_TYPE_IQ2_K
- GGML_TYPE_IQ2_KL
- GGML_TYPE_IQ2_KS
- GGML_TYPE_IQ2_KT
- GGML_TYPE_IQ2_K_R4
- GGML_TYPE_IQ2_S
- GGML_TYPE_IQ2_S_R4
- GGML_TYPE_IQ2_XS
- GGML_TYPE_IQ2_XS_R4
- GGML_TYPE_IQ2_XXS
- GGML_TYPE_IQ2_XXS_R4
- GGML_TYPE_IQ3_K
- GGML_TYPE_IQ3_KS
- GGML_TYPE_IQ3_KT
- GGML_TYPE_IQ3_K_R4
- GGML_TYPE_IQ3_S
- GGML_TYPE_IQ3_S_R4
- GGML_TYPE_IQ3_XXS
- GGML_TYPE_IQ3_XXS_R4
- GGML_TYPE_IQ4_K
- GGML_TYPE_IQ4_KS
- GGML_TYPE_IQ4_KSS
- GGML_TYPE_IQ4_KS_R4
- GGML_TYPE_IQ4_KT
- GGML_TYPE_IQ4_K_R4
- GGML_TYPE_IQ4_NL
- GGML_TYPE_IQ4_NL_R4
- GGML_TYPE_IQ4_XS
- GGML_TYPE_IQ4_XS_R8
- GGML_TYPE_IQ5_K
- GGML_TYPE_IQ5_KS
- GGML_TYPE_IQ5_KS_R4
- GGML_TYPE_IQ5_K_R4
- GGML_TYPE_IQ6_K
- GGML_TYPE_MXFP4
- GGML_TYPE_Q1_0_G128
- GGML_TYPE_Q2_K
- GGML_TYPE_Q2_K_R4
- GGML_TYPE_Q3_K
- GGML_TYPE_Q3_K_R4
- GGML_TYPE_Q4_0
- GGML_TYPE_Q4_0_4_4
- GGML_TYPE_Q4_0_4_8
- GGML_TYPE_Q4_0_8_8
- GGML_TYPE_Q4_0_R8
- GGML_TYPE_Q4_1
- GGML_TYPE_Q4_K
- GGML_TYPE_Q4_K_R4
- GGML_TYPE_Q5_0
- GGML_TYPE_Q5_0_R4
- GGML_TYPE_Q5_1
- GGML_TYPE_Q5_K
- GGML_TYPE_Q5_K_R4
- GGML_TYPE_Q6_0
- GGML_TYPE_Q6_0_R4
- GGML_TYPE_Q6_K
- GGML_TYPE_Q6_K_R4
- GGML_TYPE_Q8_0
- GGML_TYPE_Q8_0_R8
- GGML_TYPE_Q8_0_X4
- GGML_TYPE_Q8_1
- GGML_TYPE_Q8_1_X4
- GGML_TYPE_Q8_2_X4
- GGML_TYPE_Q8_K
- GGML_TYPE_Q8_K128
- GGML_TYPE_Q8_K16
- GGML_TYPE_Q8_K32
- GGML_TYPE_Q8_K64
- GGML_TYPE_Q8_KR8
- GGML_TYPE_Q8_KV
- GGML_TYPE_Q8_KV_R8
- GGML_TYPE_Q8_K_R16
- GGML_TYPE_Q8_K_R8
- GGML_UNARY_OP_ABS
- GGML_UNARY_OP_COUNT
- GGML_UNARY_OP_ELU
- GGML_UNARY_OP_EXP
- GGML_UNARY_OP_GELU
- GGML_UNARY_OP_GELU_ERF
- GGML_UNARY_OP_GELU_QUICK
- GGML_UNARY_OP_HARDSIGMOID
- GGML_UNARY_OP_HARDSWISH
- GGML_UNARY_OP_NEG
- GGML_UNARY_OP_RELU
- GGML_UNARY_OP_SGN
- GGML_UNARY_OP_SIGMOID
- GGML_UNARY_OP_SILU
- GGML_UNARY_OP_SOFTPLUS
- GGML_UNARY_OP_STEP
- GGML_UNARY_OP_SWIGLU
- GGML_UNARY_OP_SWIGLU_OAI
- GGML_UNARY_OP_TANH
- GGUF_TYPE_ARRAY
- GGUF_TYPE_BOOL
- GGUF_TYPE_COUNT
- GGUF_TYPE_FLOAT32
- GGUF_TYPE_FLOAT64
- GGUF_TYPE_INT16
- GGUF_TYPE_INT32
- GGUF_TYPE_INT64
- GGUF_TYPE_INT8
- GGUF_TYPE_STRING
- GGUF_TYPE_UINT16
- GGUF_TYPE_UINT32
- GGUF_TYPE_UINT64
- GGUF_TYPE_UINT8
- LLAMA_ATTENTION_TYPE_CAUSAL
- LLAMA_ATTENTION_TYPE_NON_CAUSAL
- LLAMA_ATTENTION_TYPE_UNSPECIFIED
- LLAMA_FLASH_ATTN_TYPE_AUTO
- LLAMA_FLASH_ATTN_TYPE_DISABLED
- LLAMA_FLASH_ATTN_TYPE_ENABLED
- LLAMA_FTYPE_ALL_F32
- LLAMA_FTYPE_GUESSED
- LLAMA_FTYPE_MOSTLY_BF16
- LLAMA_FTYPE_MOSTLY_BF16_R16
- LLAMA_FTYPE_MOSTLY_F16
- LLAMA_FTYPE_MOSTLY_IQ1_BN
- LLAMA_FTYPE_MOSTLY_IQ1_KT
- LLAMA_FTYPE_MOSTLY_IQ1_M
- LLAMA_FTYPE_MOSTLY_IQ1_M_R4
- LLAMA_FTYPE_MOSTLY_IQ1_S
- LLAMA_FTYPE_MOSTLY_IQ1_S_R4
- LLAMA_FTYPE_MOSTLY_IQ2_BN
- LLAMA_FTYPE_MOSTLY_IQ2_BN_R4
- LLAMA_FTYPE_MOSTLY_IQ2_K
- LLAMA_FTYPE_MOSTLY_IQ2_KL
- LLAMA_FTYPE_MOSTLY_IQ2_KS
- LLAMA_FTYPE_MOSTLY_IQ2_KT
- LLAMA_FTYPE_MOSTLY_IQ2_K_R4
- LLAMA_FTYPE_MOSTLY_IQ2_M
- LLAMA_FTYPE_MOSTLY_IQ2_M_R4
- LLAMA_FTYPE_MOSTLY_IQ2_S
- LLAMA_FTYPE_MOSTLY_IQ2_XS
- LLAMA_FTYPE_MOSTLY_IQ2_XS_R4
- LLAMA_FTYPE_MOSTLY_IQ2_XXS
- LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4
- LLAMA_FTYPE_MOSTLY_IQ3_K
- LLAMA_FTYPE_MOSTLY_IQ3_KL
- LLAMA_FTYPE_MOSTLY_IQ3_KS
- LLAMA_FTYPE_MOSTLY_IQ3_KT
- LLAMA_FTYPE_MOSTLY_IQ3_K_R4
- LLAMA_FTYPE_MOSTLY_IQ3_M
- LLAMA_FTYPE_MOSTLY_IQ3_S
- LLAMA_FTYPE_MOSTLY_IQ3_S_R4
- LLAMA_FTYPE_MOSTLY_IQ3_XS
- LLAMA_FTYPE_MOSTLY_IQ3_XXS
- LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4
- LLAMA_FTYPE_MOSTLY_IQ4_K
- LLAMA_FTYPE_MOSTLY_IQ4_KS
- LLAMA_FTYPE_MOSTLY_IQ4_KSS
- LLAMA_FTYPE_MOSTLY_IQ4_KS_R4
- LLAMA_FTYPE_MOSTLY_IQ4_KT
- LLAMA_FTYPE_MOSTLY_IQ4_K_R4
- LLAMA_FTYPE_MOSTLY_IQ4_NL
- LLAMA_FTYPE_MOSTLY_IQ4_NL_R4
- LLAMA_FTYPE_MOSTLY_IQ4_XS
- LLAMA_FTYPE_MOSTLY_IQ4_XS_R8
- LLAMA_FTYPE_MOSTLY_IQ5_K
- LLAMA_FTYPE_MOSTLY_IQ5_KS
- LLAMA_FTYPE_MOSTLY_IQ5_KS_R4
- LLAMA_FTYPE_MOSTLY_IQ5_K_R4
- LLAMA_FTYPE_MOSTLY_IQ6_K
- LLAMA_FTYPE_MOSTLY_MXFP4
- LLAMA_FTYPE_MOSTLY_Q1_0_G128
- LLAMA_FTYPE_MOSTLY_Q2_K
- LLAMA_FTYPE_MOSTLY_Q2_K_R4
- LLAMA_FTYPE_MOSTLY_Q2_K_S
- LLAMA_FTYPE_MOSTLY_Q3_K_L
- LLAMA_FTYPE_MOSTLY_Q3_K_M
- LLAMA_FTYPE_MOSTLY_Q3_K_R4
- LLAMA_FTYPE_MOSTLY_Q3_K_S
- LLAMA_FTYPE_MOSTLY_Q4_0
- LLAMA_FTYPE_MOSTLY_Q4_0_4_4
- LLAMA_FTYPE_MOSTLY_Q4_0_4_8
- LLAMA_FTYPE_MOSTLY_Q4_0_8_8
- LLAMA_FTYPE_MOSTLY_Q4_0_R8
- LLAMA_FTYPE_MOSTLY_Q4_1
- LLAMA_FTYPE_MOSTLY_Q4_K_M
- LLAMA_FTYPE_MOSTLY_Q4_K_R4
- LLAMA_FTYPE_MOSTLY_Q4_K_S
- LLAMA_FTYPE_MOSTLY_Q5_0
- LLAMA_FTYPE_MOSTLY_Q5_0_R4
- LLAMA_FTYPE_MOSTLY_Q5_1
- LLAMA_FTYPE_MOSTLY_Q5_K_M
- LLAMA_FTYPE_MOSTLY_Q5_K_R4
- LLAMA_FTYPE_MOSTLY_Q5_K_S
- LLAMA_FTYPE_MOSTLY_Q6_0
- LLAMA_FTYPE_MOSTLY_Q6_0_R4
- LLAMA_FTYPE_MOSTLY_Q6_K
- LLAMA_FTYPE_MOSTLY_Q6_K_R4
- LLAMA_FTYPE_MOSTLY_Q8_0
- LLAMA_FTYPE_MOSTLY_Q8_0_R8
- LLAMA_FTYPE_MOSTLY_Q8_KV
- LLAMA_FTYPE_MOSTLY_Q8_KV_R8
- LLAMA_FTYPE_MOSTLY_Q8_K_R8
- LLAMA_KV_OVERRIDE_TYPE_BOOL
- LLAMA_KV_OVERRIDE_TYPE_FLOAT
- LLAMA_KV_OVERRIDE_TYPE_INT
- LLAMA_KV_OVERRIDE_TYPE_STR
- LLAMA_POOLING_TYPE_CLS
- LLAMA_POOLING_TYPE_LAST
- LLAMA_POOLING_TYPE_MEAN
- LLAMA_POOLING_TYPE_NONE
- LLAMA_POOLING_TYPE_UNSPECIFIED
- LLAMA_ROPE_SCALING_TYPE_LINEAR
- LLAMA_ROPE_SCALING_TYPE_LONGROPE
- LLAMA_ROPE_SCALING_TYPE_MAX_VALUE
- LLAMA_ROPE_SCALING_TYPE_NONE
- LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED
- LLAMA_ROPE_SCALING_TYPE_YARN
- LLAMA_ROPE_TYPE_IMROPE
- LLAMA_ROPE_TYPE_MROPE
- LLAMA_ROPE_TYPE_NEOX
- LLAMA_ROPE_TYPE_NONE
- LLAMA_ROPE_TYPE_NORM
- LLAMA_ROPE_TYPE_VISION
- LLAMA_RS_STATUS_ALLOCATION_FAILED
- LLAMA_RS_STATUS_EXCEPTION
- LLAMA_RS_STATUS_INVALID_ARGUMENT
- LLAMA_RS_STATUS_OK
- LLAMA_SPEC_CKPT_AUTO
- LLAMA_SPEC_CKPT_CPU
- LLAMA_SPEC_CKPT_GPU_FALLBACK
- LLAMA_SPEC_CKPT_NONE
- LLAMA_SPEC_CKPT_PER_STEP
- LLAMA_SPLIT_MODE_ATTN
- LLAMA_SPLIT_MODE_GRAPH
- LLAMA_SPLIT_MODE_LAYER
- LLAMA_SPLIT_MODE_NONE
- LLAMA_TOKEN_ATTR_BYTE
- LLAMA_TOKEN_ATTR_CONTROL
- LLAMA_TOKEN_ATTR_LSTRIP
- LLAMA_TOKEN_ATTR_NORMAL
- LLAMA_TOKEN_ATTR_NORMALIZED
- LLAMA_TOKEN_ATTR_RSTRIP
- LLAMA_TOKEN_ATTR_SINGLE_WORD
- LLAMA_TOKEN_ATTR_UNDEFINED
- LLAMA_TOKEN_ATTR_UNKNOWN
- LLAMA_TOKEN_ATTR_UNUSED
- LLAMA_TOKEN_ATTR_USER_DEFINED
- LLAMA_TOKEN_TYPE_BYTE
- LLAMA_TOKEN_TYPE_CONTROL
- LLAMA_TOKEN_TYPE_NORMAL
- LLAMA_TOKEN_TYPE_UNDEFINED
- LLAMA_TOKEN_TYPE_UNKNOWN
- LLAMA_TOKEN_TYPE_UNUSED
- LLAMA_TOKEN_TYPE_USER_DEFINED
- LLAMA_VOCAB_TYPE_BPE
- LLAMA_VOCAB_TYPE_NONE
- LLAMA_VOCAB_TYPE_PLAMO2
- LLAMA_VOCAB_TYPE_RWKV
- LLAMA_VOCAB_TYPE_SPM
- LLAMA_VOCAB_TYPE_UGM
- LLAMA_VOCAB_TYPE_WPM
- MTP_OP_DRAFT_GEN
- MTP_OP_NONE
- MTP_OP_UPDATE_ACCEPTED
- MTP_OP_WARMUP