/**
 * llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
 *
 * MIT License
 *
 * Copyright (c) 2023-2024 The ggml authors
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in all
 * copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include "common.cuh"

#define CUDA_NEG_BLOCK_SIZE 256
#define CUDA_STEP_BLOCK_SIZE 256
#define CUDA_GELU_BLOCK_SIZE 256
#define CUDA_SILU_BLOCK_SIZE 256
#define CUDA_TANH_BLOCK_SIZE 256
#define CUDA_RELU_BLOCK_SIZE 256
#define CUDA_SIGMOID_BLOCK_SIZE 256
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
#define CUDA_EXP_BLOCK_SIZE 256
#define CUDA_HARDSWISH_BLOCK_SIZE 256
#define CUDA_SQR_BLOCK_SIZE 256
#define CUDA_SQRT_BLOCK_SIZE 256
#define CUDA_SIN_BLOCK_SIZE 256
#define CUDA_COS_BLOCK_SIZE 256

void ggml_cuda_op_neg(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_step(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_silu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_gelu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_tanh(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_sigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_exp(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_leaky_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_sin(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

void ggml_cuda_op_cos(ggml_backend_cuda_context & ctx, ggml_tensor * dst);