GGML_GLU_OP_REGLU       GLU Operation Types
GGML_SORT_ORDER_ASC     Sort Order Constants
GGML_TYPE_F32           GGML Data Types
ag_add                  Element-wise addition with broadcasting
ag_batch_norm           Create a Batch Normalisation layer
ag_clamp                Element-wise clamp
ag_cross_entropy_loss   Categorical Cross-Entropy loss
ag_dataloader           Create a mini-batch data loader
ag_default_device       Return the current default compute device
ag_default_dtype        Return the current default dtype for GPU
                        operations
ag_device               Set the default compute device for ag_*
                        operations
ag_dropout              Create a Dropout layer
ag_dtype                Set the default floating-point precision for
                        ag_* GPU operations
ag_embedding            Create an Embedding layer
ag_eval                 Switch a layer or sequential model to eval mode
ag_exp                  Element-wise exponential
ag_gradcheck            Numerical gradient check (like
                        torch.autograd.gradcheck)
ag_linear               Create a dense layer with learnable parameters
ag_log                  Element-wise natural logarithm
ag_matmul               Matrix multiplication
ag_mean                 Mean of elements (or along a dim)
ag_mse_loss             Mean Squared Error loss
ag_mul                  Element-wise multiplication
ag_multihead_attention
                        Create a Multi-Head Attention layer
ag_param                Create a parameter tensor (gradient tracked)
ag_pow                  Element-wise power
ag_relu                 ReLU activation
ag_reshape              Reshape tensor
ag_scale                Scale tensor by a scalar constant
ag_sequential           Create a sequential container of layers
ag_sigmoid              Sigmoid activation
ag_softmax              Softmax activation (column-wise)
ag_softmax_cross_entropy_loss
                        Fused softmax + cross-entropy loss (numerically
                        stable)
ag_sub                  Element-wise subtraction
ag_sum                  Sum all elements (or along a dim): out = sum(x)
ag_tanh                 Tanh activation
ag_tensor               Create a dynamic tensor (no gradient tracking)
ag_to_device            Move a tensor to the specified device
ag_train                Switch a layer or sequential model to training
                        mode
ag_transpose            Transpose a tensor
backward                Run backward pass from a scalar loss tensor
clip_grad_norm          Clip gradients by global L2 norm
dequantize_row_iq2_xxs
                        Dequantize Row (IQ)
dequantize_row_mxfp4    Dequantize Row (MXFP4)
dequantize_row_q2_K     Dequantize Row (K-quants)
dequantize_row_q4_0     Dequantize Row (Q4_0)
dequantize_row_tq1_0    Dequantize Row (Ternary)
dp_train                Data-parallel training across multiple GPUs
ggml_abort_is_r_enabled
                        Check if R Abort Handler is Enabled
ggml_abs                Absolute Value (Graph)
ggml_abs_inplace        Absolute Value In-place (Graph)
ggml_add                Add tensors
ggml_add1               Add Scalar to Tensor (Graph)
ggml_add_inplace        Element-wise Addition In-place (Graph)
ggml_apply              Apply a Layer Object to a Tensor Node
ggml_are_same_layout    Check if Two Tensors Have the Same Layout
ggml_are_same_shape     Compare Tensor Shapes
ggml_are_same_stride    Compare Tensor Strides
ggml_argmax             Argmax (Graph)
ggml_argsort            Argsort - Get Sorting Indices (Graph)
ggml_backend_alloc_ctx_tensors
                        Allocate Context Tensors to Backend
ggml_backend_buffer_clear
                        Clear buffer memory
ggml_backend_buffer_free
                        Free Backend Buffer
ggml_backend_buffer_get_size
                        Get Backend Buffer Size
ggml_backend_buffer_get_usage
                        Get buffer usage
ggml_backend_buffer_is_host
                        Check if buffer is host memory
ggml_backend_buffer_is_multi_buffer
                        Check if buffer is a multi-buffer
ggml_backend_buffer_name
                        Get Backend Buffer Name
ggml_backend_buffer_reset
                        Reset buffer
ggml_backend_buffer_set_usage
                        Set buffer usage hint
ggml_backend_buffer_usage_any
                        Buffer usage: Any
ggml_backend_buffer_usage_compute
                        Buffer usage: Compute
ggml_backend_buffer_usage_weights
                        Buffer usage: Weights
ggml_backend_cpu_init   Initialize CPU Backend
ggml_backend_cpu_set_n_threads
                        Set CPU Backend Threads
ggml_backend_dev_by_name
                        Get device by name
ggml_backend_dev_by_type
                        Get device by type
ggml_backend_dev_count
                        Get number of available devices
ggml_backend_dev_description
                        Get device description
ggml_backend_dev_get    Get device by index
ggml_backend_dev_get_props
                        Get device properties
ggml_backend_dev_init   Initialize backend from device
ggml_backend_dev_memory
                        Get device memory
ggml_backend_dev_name   Get device name
ggml_backend_dev_offload_op
                        Check if device should offload operation
ggml_backend_dev_supports_buft
                        Check if device supports buffer type
ggml_backend_dev_supports_op
                        Check if device supports operation
ggml_backend_dev_type   Get device type
ggml_backend_device_register
                        Register a device
ggml_backend_device_type_accel
                        Device type: Accelerator
ggml_backend_device_type_cpu
                        Device type: CPU
ggml_backend_device_type_gpu
                        Device type: GPU
ggml_backend_device_type_igpu
                        Device type: Integrated GPU
ggml_backend_event_free
                        Free event
ggml_backend_event_new
                        Create new event
ggml_backend_event_record
                        Record event
ggml_backend_event_synchronize
                        Synchronize event
ggml_backend_event_wait
                        Wait for event
ggml_backend_free       Free Backend
ggml_backend_get_device
                        Get device from backend
ggml_backend_graph_compute
                        Compute Graph with Backend
ggml_backend_graph_compute_async
                        Compute graph asynchronously
ggml_backend_graph_plan_compute
                        Execute graph plan
ggml_backend_graph_plan_create
                        Create graph execution plan
ggml_backend_graph_plan_free
                        Free graph execution plan
ggml_backend_init_best
                        Initialize best available backend
ggml_backend_init_by_name
                        Initialize backend by name
ggml_backend_init_by_type
                        Initialize backend by type
ggml_backend_load       Load backend from dynamic library
ggml_backend_load_all   Load all available backends
ggml_backend_multi_buffer_alloc_buffer
                        Allocate multi-buffer
ggml_backend_multi_buffer_set_usage
                        Set usage for all buffers in a multi-buffer
ggml_backend_name       Get Backend Name
ggml_backend_reg_by_name
                        Get backend registry by name
ggml_backend_reg_count
                        Get number of registered backends
ggml_backend_reg_dev_count
                        Get number of devices in registry
ggml_backend_reg_dev_get
                        Get device from registry
ggml_backend_reg_get    Get backend registry by index
ggml_backend_reg_name   Get registry name
ggml_backend_register   Register a backend
ggml_backend_sched_alloc_graph
                        Allocate graph on scheduler
ggml_backend_sched_free
                        Free backend scheduler
ggml_backend_sched_get_backend
                        Get backend from scheduler
ggml_backend_sched_get_n_backends
                        Get number of backends in scheduler
ggml_backend_sched_get_n_copies
                        Get number of tensor copies
ggml_backend_sched_get_n_splits
                        Get number of graph splits
ggml_backend_sched_get_tensor_backend
                        Get tensor backend assignment
ggml_backend_sched_graph_compute
                        Compute graph using scheduler
ggml_backend_sched_graph_compute_async
                        Compute graph asynchronously
ggml_backend_sched_new
                        Create a new backend scheduler
ggml_backend_sched_reserve
                        Reserve memory for scheduler
ggml_backend_sched_reset
                        Reset scheduler
ggml_backend_sched_set_tensor_backend
                        Set tensor backend assignment
ggml_backend_sched_synchronize
                        Synchronize scheduler
ggml_backend_synchronize
                        Synchronize backend
ggml_backend_tensor_copy_async
                        Copy tensor asynchronously between backends
ggml_backend_tensor_get_and_sync
                        Backend Tensor Get and Sync
ggml_backend_tensor_get_async
                        Get tensor data asynchronously
ggml_backend_tensor_get_data
                        Get Tensor Data via Backend
ggml_backend_tensor_get_f32_first
                        Get First Float from Backend Tensor
ggml_backend_tensor_set_async
                        Set tensor data asynchronously
ggml_backend_tensor_set_data
                        Set Tensor Data via Backend
ggml_backend_unload     Unload backend
ggml_batch_norm         Create a Batch Normalization Layer Object
ggml_blck_size          Get Block Size
ggml_build_forward_expand
                        Build forward expand
ggml_callback_early_stopping
                        Early stopping callback
ggml_can_repeat         Check If Tensor Can Be Repeated
ggml_ceil               Ceiling (Graph)
ggml_ceil_inplace       Ceiling In-place (Graph)
ggml_clamp              Clamp (Graph)
ggml_compile.ggml_functional_model
                        Compile a Sequential Model
ggml_concat             Concatenate Tensors (Graph)
ggml_cont               Make Contiguous (Graph)
ggml_conv_1d            1D Convolution (Graph)
ggml_conv_2d            2D Convolution (Graph)
ggml_conv_transpose_1d
                        Transposed 1D Convolution (Graph)
ggml_cos                Cosine (Graph)
ggml_count_equal        Count Equal Elements (Graph)
ggml_cpu_add            Element-wise Addition (CPU Direct)
ggml_cpu_features       Get All CPU Features
ggml_cpu_get_rvv_vlen   Get RISC-V Vector Length
ggml_cpu_get_sve_cnt    Get SVE Vector Length (ARM)
ggml_cpu_has_amx_int8   CPU Feature Detection - AMX INT8
ggml_cpu_has_arm_fma    CPU Feature Detection - ARM FMA
ggml_cpu_has_avx        CPU Feature Detection - AVX
ggml_cpu_has_avx2       CPU Feature Detection - AVX2
ggml_cpu_has_avx512     CPU Feature Detection - AVX-512
ggml_cpu_has_avx512_bf16
                        CPU Feature Detection - AVX-512 BF16
ggml_cpu_has_avx512_vbmi
                        CPU Feature Detection - AVX-512 VBMI
ggml_cpu_has_avx512_vnni
                        CPU Feature Detection - AVX-512 VNNI
ggml_cpu_has_avx_vnni   CPU Feature Detection - AVX-VNNI
ggml_cpu_has_bmi2       CPU Feature Detection - BMI2
ggml_cpu_has_dotprod    CPU Feature Detection - Dot Product (ARM)
ggml_cpu_has_f16c       CPU Feature Detection - F16C
ggml_cpu_has_fma        CPU Feature Detection - FMA
ggml_cpu_has_fp16_va    CPU Feature Detection - FP16 Vector Arithmetic
                        (ARM)
ggml_cpu_has_llamafile
                        CPU Feature Detection - Llamafile
ggml_cpu_has_matmul_int8
                        CPU Feature Detection - INT8 Matrix Multiply
                        (ARM)
ggml_cpu_has_neon       CPU Feature Detection - NEON (ARM)
ggml_cpu_has_riscv_v    CPU Feature Detection - RISC-V Vector
ggml_cpu_has_sme        CPU Feature Detection - SME (ARM)
ggml_cpu_has_sse3       CPU Feature Detection - SSE3
ggml_cpu_has_ssse3      CPU Feature Detection - SSSE3
ggml_cpu_has_sve        CPU Feature Detection - SVE (ARM)
ggml_cpu_has_vsx        CPU Feature Detection - VSX (PowerPC)
ggml_cpu_has_vxe        CPU Feature Detection - VXE (IBM
                        z/Architecture)
ggml_cpu_has_wasm_simd
                        CPU Feature Detection - WebAssembly SIMD
ggml_cpu_mul            Element-wise Multiplication (CPU Direct)
ggml_cpy                Copy Tensor with Type Conversion (Graph)
ggml_cycles             Get CPU Cycles
ggml_cycles_per_ms      Get CPU Cycles per Millisecond
ggml_dense              Create a Dense Layer Object
ggml_diag               Diagonal Matrix (Graph)
ggml_diag_mask_inf      Diagonal Mask with -Inf (Graph)
ggml_diag_mask_inf_inplace
                        Diagonal Mask with -Inf In-place (Graph)
ggml_diag_mask_zero     Diagonal Mask with Zero (Graph)
ggml_div                Element-wise Division (Graph)
ggml_div_inplace        Element-wise Division In-place (Graph)
ggml_dup                Duplicate Tensor (Graph)
ggml_dup_inplace        Duplicate Tensor In-place (Graph)
ggml_dup_tensor         Duplicate Tensor
ggml_element_size       Get Element Size
ggml_elu                ELU Activation (Graph)
ggml_elu_inplace        ELU Activation In-place (Graph)
ggml_embedding          Create an Embedding Layer Object
ggml_estimate_memory    Estimate Required Memory
ggml_evaluate.ggml_functional_model
                        Evaluate a Trained Model
ggml_exp                Exponential (Graph)
ggml_exp_inplace        Exponential In-place (Graph)
ggml_fit.ggml_functional_model
                        Train a Model (dispatcher)
ggml_fit_opt            Fit model with R-side epoch loop and callbacks
ggml_flash_attn_back    Flash Attention Backward (Graph)
ggml_flash_attn_ext     Flash Attention (Graph)
ggml_floor              Floor (Graph)
ggml_floor_inplace      Floor In-place (Graph)
ggml_free               Free GGML context
ggml_freeze_weights     Freeze Layer Weights
ggml_ftype_to_ggml_type
                        Convert ftype to ggml_type
ggml_gallocr_alloc_graph
                        Allocate Memory for Graph
ggml_gallocr_free       Free Graph Allocator
ggml_gallocr_get_buffer_size
                        Get Graph Allocator Buffer Size
ggml_gallocr_new        Create Graph Allocator
ggml_gallocr_reserve    Reserve Memory for Graph
ggml_geglu              GeGLU (GELU Gated Linear Unit) (Graph)
ggml_geglu_quick        GeGLU Quick (Fast GeGLU) (Graph)
ggml_geglu_split        GeGLU Split (Graph)
ggml_gelu               GELU Activation (Graph)
ggml_gelu_erf           Exact GELU Activation (Graph)
ggml_gelu_inplace       GELU Activation In-place (Graph)
ggml_gelu_quick         GELU Quick Activation (Graph)
ggml_get_f32            Get F32 data
ggml_get_f32_nd         Get Single Float Value by N-D Index
ggml_get_first_tensor   Get First Tensor from Context
ggml_get_i32            Get I32 Data
ggml_get_i32_nd         Get Single Int32 Value by N-D Index
ggml_get_layer          Get a Layer from a Sequential Model
ggml_get_max_tensor_size
                        Get Maximum Tensor Size
ggml_get_mem_size       Get Context Memory Size
ggml_get_n_threads      Get Number of Threads
ggml_get_name           Get Tensor Name
ggml_get_next_tensor    Get Next Tensor from Context
ggml_get_no_alloc       Get No Allocation Mode
ggml_get_op_params      Get Tensor Operation Parameters
ggml_get_op_params_f32
                        Get Float Op Parameter
ggml_get_op_params_i32
                        Get Integer Op Parameter
ggml_get_rows           Get Rows by Indices (Graph)
ggml_get_rows_back      Get Rows Backward (Graph)
ggml_get_unary_op       Get Unary Operation from Tensor
ggml_glu                Generic GLU (Gated Linear Unit) (Graph)
ggml_glu_split          Generic GLU Split (Graph)
ggml_graph_compute      Compute graph
ggml_graph_compute_with_ctx
                        Compute Graph with Context (Alternative Method)
ggml_graph_dump_dot     Export Graph to DOT Format
ggml_graph_get_tensor   Get Tensor from Graph by Name
ggml_graph_n_nodes      Get Number of Nodes in Graph
ggml_graph_node         Get Graph Node
ggml_graph_overhead     Get Graph Overhead
ggml_graph_print        Print Graph Information
ggml_graph_reset        Reset Graph (for backpropagation)
ggml_graph_view         Create a View of a Subgraph
ggml_group_norm         Group Normalization (Graph)
ggml_group_norm_inplace
                        Group Normalization In-place (Graph)
ggml_gru                Create a GRU Layer Object
ggml_hardsigmoid        Hard Sigmoid Activation (Graph)
ggml_hardswish          Hard Swish Activation (Graph)
ggml_im2col             Image to Column (Graph)
ggml_init               Initialize GGML context
ggml_init_auto          Create Context with Auto-sizing
ggml_input              Declare a Functional API Input Tensor
ggml_is_available       Check if GGML is available
ggml_is_contiguous      Check if Tensor is Contiguous
ggml_is_contiguous_0    Check Tensor Contiguity (Dimension 0)
ggml_is_contiguous_1    Check Tensor Contiguity (Dimensions >= 1)
ggml_is_contiguous_2    Check Tensor Contiguity (Dimensions >= 2)
ggml_is_contiguous_channels
                        Check Channel-wise Contiguity
ggml_is_contiguous_rows
                        Check Row-wise Contiguity
ggml_is_contiguously_allocated
                        Check If Tensor is Contiguously Allocated
ggml_is_permuted        Check if Tensor is Permuted
ggml_is_quantized       Check If Type is Quantized
ggml_is_transposed      Check if Tensor is Transposed
ggml_l2_norm            L2 Normalization (Graph)
ggml_l2_norm_inplace    L2 Normalization In-place (Graph)
ggml_layer_add          Element-wise Addition of Two Tensor Nodes
ggml_layer_batch_norm   Add Batch Normalization Layer
ggml_layer_concatenate
                        Concatenate Tensor Nodes Along an Axis
ggml_layer_conv_1d      Create a Conv1D Layer Object
ggml_layer_conv_2d      Create a Conv2D Layer Object
ggml_layer_dense        Add Dense (Fully Connected) Layer
ggml_layer_dropout      Add Dropout Layer
ggml_layer_embedding    Add Embedding Layer
ggml_layer_flatten      Add Flatten Layer
ggml_layer_global_average_pooling_2d
                        Global Average Pooling for 2D Feature Maps
ggml_layer_global_max_pooling_2d
                        Global Max Pooling for 2D Feature Maps
ggml_layer_gru          Add a GRU Layer
ggml_layer_lstm         Add an LSTM Layer
ggml_layer_max_pooling_2d
                        Add 2D Max Pooling Layer
ggml_leaky_relu         Leaky ReLU Activation (Graph)
ggml_load_model         Load a Full Model (Architecture + Weights)
ggml_load_weights       Load Model Weights from File
ggml_log                Natural Logarithm (Graph)
ggml_log_inplace        Natural Logarithm In-place (Graph)
ggml_log_is_r_enabled   Check if R Logging is Enabled
ggml_log_set_default    Restore Default GGML Logging
ggml_log_set_r          Enable R-compatible GGML Logging
ggml_lstm               Create an LSTM Layer Object
ggml_mean               Mean (Graph)
ggml_model              Create a Functional Model
ggml_model_sequential   Create a Sequential Neural Network Model
ggml_mul                Multiply tensors
ggml_mul_inplace        Element-wise Multiplication In-place (Graph)
ggml_mul_mat            Matrix Multiplication (Graph)
ggml_mul_mat_id         Matrix Multiplication with Expert Selection
                        (Graph)
ggml_n_dims             Get Number of Dimensions
ggml_nbytes             Get number of bytes
ggml_neg                Negation (Graph)
ggml_neg_inplace        Negation In-place (Graph)
ggml_nelements          Get number of elements
ggml_new_f32            Create Scalar F32 Tensor
ggml_new_i32            Create Scalar I32 Tensor
ggml_new_tensor         Create Tensor with Arbitrary Dimensions
ggml_new_tensor_1d      Create 1D tensor
ggml_new_tensor_2d      Create 2D tensor
ggml_new_tensor_3d      Create 3D Tensor
ggml_new_tensor_4d      Create 4D Tensor
ggml_norm               Layer Normalization (Graph)
ggml_norm_inplace       Layer Normalization In-place (Graph)
ggml_nrows              Get Number of Rows
ggml_op_can_inplace     Check if Operation Can Be Done In-place
ggml_op_desc            Get Operation Description from Tensor
ggml_op_name            Get Operation Name
ggml_op_symbol          Get Operation Symbol
ggml_opt_alloc          Allocate graph for evaluation
ggml_opt_context_optimizer_type
                        Get optimizer type from context
ggml_opt_dataset_data   Get data tensor from dataset
ggml_opt_dataset_free   Free optimization dataset
ggml_opt_dataset_get_batch
                        Get batch from dataset
ggml_opt_dataset_init   Create a new optimization dataset
ggml_opt_dataset_labels
                        Get labels tensor from dataset
ggml_opt_dataset_ndata
                        Get number of datapoints in dataset
ggml_opt_dataset_shuffle
                        Shuffle dataset
ggml_opt_default_params
                        Get default optimizer parameters
ggml_opt_epoch          Run one training epoch
ggml_opt_eval           Evaluate model
ggml_opt_fit            Fit model to dataset
ggml_opt_free           Free optimizer context
ggml_opt_get_lr         Get current learning rate from optimizer
                        context
ggml_opt_grad_acc       Get gradient accumulator for a tensor
ggml_opt_init           Initialize optimizer context
ggml_opt_init_for_fit   Initialize optimizer context for R-side epoch
                        loop
ggml_opt_inputs         Get inputs tensor from optimizer context
ggml_opt_labels         Get labels tensor from optimizer context
ggml_opt_loss           Get loss tensor from optimizer context
ggml_opt_loss_type_cross_entropy
                        Loss type: Cross Entropy
ggml_opt_loss_type_mean
                        Loss type: Mean
ggml_opt_loss_type_mse
                        Loss type: Mean Squared Error
ggml_opt_loss_type_sum
                        Loss type: Sum
ggml_opt_ncorrect       Get number of correct predictions tensor
ggml_opt_optimizer_name
                        Get optimizer name
ggml_opt_optimizer_type_adamw
                        Optimizer type: AdamW
ggml_opt_optimizer_type_sgd
                        Optimizer type: SGD
ggml_opt_outputs        Get outputs tensor from optimizer context
ggml_opt_pred           Get predictions tensor from optimizer context
ggml_opt_prepare_alloc
                        Prepare allocation for non-static graphs
ggml_opt_reset          Reset optimizer context
ggml_opt_result_accuracy
                        Get accuracy from result
ggml_opt_result_free    Free optimization result
ggml_opt_result_init    Initialize optimization result
ggml_opt_result_loss    Get loss from result
ggml_opt_result_ndata   Get number of datapoints from result
ggml_opt_result_pred    Get predictions from result
ggml_opt_result_reset   Reset optimization result
ggml_opt_set_lr         Set learning rate in optimizer context
ggml_opt_static_graphs
                        Check if using static graphs
ggml_out_prod           Outer Product (Graph)
ggml_pad                Pad Tensor with Zeros (Graph)
ggml_permute            Permute Tensor Dimensions (Graph)
ggml_pool_1d            1D Pooling (Graph)
ggml_pool_2d            2D Pooling (Graph)
ggml_pop_layer          Remove the Last Layer from a Sequential Model
ggml_predict.ggml_functional_model
                        Get Predictions from a Trained Model
ggml_predict_classes    Predict Classes from a Trained Model
ggml_print_mem_status   Print Context Memory Status
ggml_print_objects      Print Objects in Context
ggml_quant_block_info   Get Quantization Block Info
ggml_quantize_chunk     Quantize Data Chunk
ggml_quantize_free      Free Quantization Resources
ggml_quantize_init      Initialize Quantization Tables
ggml_quantize_requires_imatrix
                        Check if Quantization Requires Importance
                        Matrix
ggml_reglu              ReGLU (ReLU Gated Linear Unit) (Graph)
ggml_reglu_split        ReGLU Split (Graph)
ggml_relu               ReLU Activation (Graph)
ggml_relu_inplace       ReLU Activation In-place (Graph)
ggml_repeat             Repeat (Graph)
ggml_repeat_back        Repeat Backward (Graph)
ggml_reset              Reset GGML Context
ggml_reshape_1d         Reshape to 1D (Graph)
ggml_reshape_2d         Reshape to 2D (Graph)
ggml_reshape_3d         Reshape to 3D (Graph)
ggml_reshape_4d         Reshape to 4D (Graph)
ggml_rms_norm           RMS Normalization (Graph)
ggml_rms_norm_back      RMS Norm Backward (Graph)
ggml_rms_norm_inplace   RMS Normalization In-place (Graph)
ggml_rope               Rotary Position Embedding (Graph)
ggml_rope_ext           Extended RoPE with Frequency Scaling (Graph)
ggml_rope_ext_back      RoPE Extended Backward (Graph)
ggml_rope_ext_inplace   Extended RoPE Inplace (Graph)
ggml_rope_inplace       Rotary Position Embedding In-place (Graph)
ggml_rope_multi         Multi-RoPE for Vision Models (Graph)
ggml_rope_multi_inplace
                        Multi-RoPE Inplace (Graph)
ggml_round              Round (Graph)
ggml_round_inplace      Round In-place (Graph)
ggml_save_model         Save a Full Model (Architecture + Weights)
ggml_save_weights       Save Model Weights to File
ggml_scale              Scale (Graph)
ggml_scale_inplace      Scale Tensor In-place (Graph)
ggml_schedule_cosine_decay
                        Cosine annealing LR scheduler
ggml_schedule_reduce_on_plateau
                        Reduce on plateau LR scheduler
ggml_schedule_step_decay
                        Step decay LR scheduler
ggml_set                Set Tensor Region (Graph)
ggml_set_1d             Set 1D Tensor Region (Graph)
ggml_set_2d             Set 2D Tensor Region (Graph)
ggml_set_abort_callback_default
                        Restore Default Abort Behavior
ggml_set_abort_callback_r
                        Enable R-compatible Abort Handling
ggml_set_f32            Set F32 data
ggml_set_f32_nd         Set Single Float Value by N-D Index
ggml_set_i32            Set I32 Data
ggml_set_i32_nd         Set Single Int32 Value by N-D Index
ggml_set_input          Mark Tensor as Input
ggml_set_n_threads      Set Number of Threads
ggml_set_name           Set Tensor Name
ggml_set_no_alloc       Set No Allocation Mode
ggml_set_op_params      Set Tensor Operation Parameters
ggml_set_op_params_f32
                        Set Float Op Parameter
ggml_set_op_params_i32
                        Set Integer Op Parameter
ggml_set_output         Mark Tensor as Output
ggml_set_param          Set Tensor as Trainable Parameter
ggml_set_zero           Set Tensor to Zero
ggml_sgn                Sign Function (Graph)
ggml_sigmoid            Sigmoid Activation (Graph)
ggml_sigmoid_inplace    Sigmoid Activation In-place (Graph)
ggml_silu               SiLU Activation (Graph)
ggml_silu_back          SiLU Backward (Graph)
ggml_silu_inplace       SiLU Activation In-place (Graph)
ggml_sin                Sine (Graph)
ggml_soft_max           Softmax (Graph)
ggml_soft_max_ext       Extended Softmax with Masking and Scaling
                        (Graph)
ggml_soft_max_ext_back
                        Softmax Backward Extended (Graph)
ggml_soft_max_ext_back_inplace
                        Extended Softmax Backward Inplace (Graph)
ggml_soft_max_ext_inplace
                        Extended Softmax Inplace (Graph)
ggml_soft_max_inplace   Softmax In-place (Graph)
ggml_softplus           Softplus Activation (Graph)
ggml_softplus_inplace   Softplus Activation In-place (Graph)
ggml_sqr                Square (Graph)
ggml_sqr_inplace        Square In-place (Graph)
ggml_sqrt               Square Root (Graph)
ggml_sqrt_inplace       Square Root In-place (Graph)
ggml_step               Step Function (Graph)
ggml_sub                Element-wise Subtraction (Graph)
ggml_sub_inplace        Element-wise Subtraction In-place (Graph)
ggml_sum                Sum (Graph)
ggml_sum_rows           Sum Rows (Graph)
ggml_swiglu             SwiGLU (Swish/SiLU Gated Linear Unit) (Graph)
ggml_swiglu_split       SwiGLU Split (Graph)
ggml_tanh               Tanh Activation (Graph)
ggml_tanh_inplace       Tanh Activation In-place (Graph)
ggml_tensor_copy        Copy Tensor Data
ggml_tensor_nb          Get Tensor Strides (nb)
ggml_tensor_num         Count Tensors in Context
ggml_tensor_overhead    Get Tensor Overhead
ggml_tensor_set_f32_scalar
                        Fill Tensor with Scalar
ggml_tensor_shape       Get Tensor Shape
ggml_tensor_type        Get Tensor Type
ggml_test               Test GGML
ggml_time_init          Initialize GGML Timer
ggml_time_ms            Get Time in Milliseconds
ggml_time_us            Get Time in Microseconds
ggml_timestep_embedding
                        Timestep Embedding (Graph Operation)
ggml_top_k              Top-K Indices (Graph)
ggml_transpose          Transpose (Graph)
ggml_type_name          Get Type Name
ggml_type_size          Get Type Size in Bytes
ggml_type_sizef         Get Type Size as Float
ggml_unary_op_name      Get Unary Operation Name
ggml_unfreeze_weights   Unfreeze Layer Weights
ggml_upscale            Upscale Tensor (Graph)
ggml_used_mem           Get Used Memory
ggml_version            Get GGML version
ggml_view_1d            1D View with Byte Offset (Graph)
ggml_view_2d            2D View with Byte Offset (Graph)
ggml_view_3d            3D View with Byte Offset (Graph)
ggml_view_4d            4D View with Byte Offset (Graph)
ggml_view_tensor        View Tensor
ggml_vulkan_available   Check if Vulkan support is available
ggml_vulkan_backend_name
                        Get Vulkan backend name
ggml_vulkan_device_count
                        Get number of Vulkan devices
ggml_vulkan_device_description
                        Get Vulkan device description
ggml_vulkan_device_memory
                        Get Vulkan device memory
ggml_vulkan_free        Free Vulkan backend
ggml_vulkan_init        Initialize Vulkan backend
ggml_vulkan_is_backend
                        Check if backend is Vulkan
ggml_vulkan_list_devices
                        List all Vulkan devices
ggml_vulkan_status      Print Vulkan status
ggml_with_temp_ctx      Execute with Temporary Context
iq2xs_free_impl         Free IQ2 Quantization Tables
iq2xs_init_impl         Initialize IQ2 Quantization Tables
iq3xs_free_impl         Free IQ3 Quantization Tables
iq3xs_init_impl         Initialize IQ3 Quantization Tables
lr_scheduler_cosine     Cosine-annealing learning rate scheduler
lr_scheduler_step       Step-decay learning rate scheduler
nn_topo_sort            Topologically sort nodes reachable from output
                        nodes
optimizer_adam          Create an Adam optimizer
optimizer_sgd           Create an SGD optimizer
plot.ggml_history       Plot training history
print.ag_tensor         Print method for ag_tensor
print.ggml_functional_model
                        Print method for ggml_functional_model
print.ggml_history      Print method for ggml_history
print.ggml_sequential_model
                        Print method for ggml_sequential_model
quantize_iq2_xxs        Quantize Data (IQ)
quantize_mxfp4          Quantize Data (MXFP4)
quantize_q2_K           Quantize Data (K-quants)
quantize_q4_0           Quantize Data (Q4_0)
quantize_row_iq3_xxs_ref
                        Quantize Row Reference (IQ)
quantize_row_mxfp4_ref
                        Quantize Row Reference (MXFP4)
quantize_row_q2_K_ref   Quantize Row Reference (K-quants)
quantize_row_q4_0_ref   Quantize Row Reference (Basic)
quantize_row_tq1_0_ref
                        Quantize Row Reference (Ternary)
quantize_tq1_0          Quantize Data (Ternary)
rope_types              RoPE Mode Constants
summary.ggml_sequential_model
                        Summary method for ggml_sequential_model
with_grad_tape          Run code with gradient tape enabled
