llama-cpp-sys-4 0.9.0

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8

#include "common.cuh"
#include "ggml.h"

void ggml_cuda_op_dsv4_hc_comb(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_dsv4_hc_pre(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
// gate_scale_in/gate_scale_out: the SCALE nodes of a fused SCALE -> SIGMOID -> SCALE chain feeding src[2]
void ggml_cuda_op_dsv4_hc_post(ggml_backend_cuda_context & ctx, ggml_tensor * dst,
        const ggml_tensor * gate_scale_in = nullptr, const ggml_tensor * gate_scale_out = nullptr);