top-k.cuh « ggml-cuda « src « ggml « llama.cpp - llmnpc - Testing how LLM's fair as NPC's

summary refs log tree commit diff

path: root/llama.cpp/ggml/src/ggml-cuda/top-k.cuh

blob: f4d8f61e5b3f14a823641883750f764c4b785024 (plain)

1
2
3

#include "common.cuh"

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