CUDA: fuse relu + sqr (#22249)
This commit is contained in:
@@ -91,6 +91,8 @@ void ggml_cuda_op_xielu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
||||
|
||||
void ggml_cuda_op_unary_mul(ggml_backend_cuda_context & ctx, ggml_tensor * unary_node, ggml_tensor * mul_node);
|
||||
|
||||
void ggml_cuda_op_relu_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * relu_node, ggml_tensor * sqr_node);
|
||||
|
||||
__device__ __forceinline__ float ggml_cuda_op_silu_single(float x) {
|
||||
return x / (1.0f + expf(-x));
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user