OpenTransformer's picture
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)
03ba2cd verified
#include "common.cuh"
void ggml_cuda_op_argsort(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
#ifdef GGML_CUDA_USE_CUB
void argsort_f32_i32_cuda_cub(ggml_cuda_pool & pool,
const float * x,
int * dst,
const int ncols,
const int nrows,
ggml_sort_order order,
cudaStream_t stream);
#endif // GGML_CUDA_USE_CUB
void argsort_f32_i32_cuda_bitonic(const float * x,
int * dst,
const int ncols,
const int nrows,
ggml_sort_order order,
cudaStream_t stream);