Repositories
ยป
llmnpc
: Testing how LLM's fair as NPC's
Commits
Files
Markers
Readme
Download
-- Select Branch --
master
Path:
llmnpc
/
llama.cpp
/
ggml
/
src
/
ggml-cuda
/ argmax.cuh (
raw
)
1
#include "common.cuh"
2
3
void ggml_cuda_argmax(ggml_backend_cuda_context & ctx, ggml_tensor * dst);