mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-24 15:14:10 +00:00
28d3e63805
* Fuse sigmoid+add+grouped_topk+get_rows (CPU) * Fix CPU + CUDA but CUDA is somehow not 100% correct as I get a slightly different PPL (lower!) * Minor * Fuse sigmoid+add+topk+get_rows (CUDA) * Fuse sigmoid+add+topk+get_rows (CPU) * Fuse topk+view+get_rows+reshape+softmax (CPU) * Fuse topk+view+get_rows+reshape+softmax (CUDA) * cpu: turn off the openai topk fusing for now Something is not right and I don't see the bug. On the CPU one doesn't gain much if anything, so not a big loss. * Also fuse sum_rows and div --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
8 lines
298 B
Plaintext
8 lines
298 B
Plaintext
#include "common.cuh"
|
|
|
|
void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void sum_rows_f32_cuda(const float * x, float * dst, const int ncols, const int nrows, cudaStream_t stream);
|
|
|
|
void ggml_cuda_op_sum_rows_div(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|