mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-24 07:04:11 +00:00
Adding forgotten file
This commit is contained in:
41
ggml/src/ggml-cuda/graph.cuh
Normal file
41
ggml/src/ggml-cuda/graph.cuh
Normal file
@@ -0,0 +1,41 @@
|
||||
#pragma once
|
||||
|
||||
struct ggml_graph_node_properties {
|
||||
void * node_address;
|
||||
ggml_op node_op;
|
||||
int64_t ne[GGML_MAX_DIMS];
|
||||
size_t nb[GGML_MAX_DIMS];
|
||||
void * src_address[GGML_MAX_SRC];
|
||||
int32_t op_params[GGML_MAX_OP_PARAMS / sizeof(int32_t)];
|
||||
};
|
||||
|
||||
struct ggml_cuda_graph {
|
||||
#ifdef USE_CUDA_GRAPH
|
||||
~ggml_cuda_graph() {
|
||||
if (instance != nullptr) {
|
||||
CUDA_CHECK(cudaGraphExecDestroy(instance));
|
||||
}
|
||||
if (graph != nullptr) {
|
||||
CUDA_CHECK(cudaGraphDestroy(graph));
|
||||
}
|
||||
}
|
||||
cudaGraph_t graph = nullptr;
|
||||
cudaGraphExec_t instance = nullptr;
|
||||
size_t num_nodes = 0;
|
||||
std::vector<cudaGraphNode_t> nodes;
|
||||
std::vector<cudaKernelNodeParams> params;
|
||||
bool disable_due_to_gpu_arch = false;
|
||||
bool disable_due_to_too_many_updates = false;
|
||||
bool disable_due_to_failed_graph_capture = false;
|
||||
int number_consecutive_updates = 0;
|
||||
std::vector<ggml_graph_node_properties> ggml_graph_properties;
|
||||
bool use_cpy_indirection = false;
|
||||
std::vector<char *> cpy_dest_ptrs;
|
||||
char ** dest_ptrs_d;
|
||||
int dest_ptrs_size = 0;
|
||||
// Index to allow each cpy kernel to be aware of it's position within the graph
|
||||
// relative to other cpy nodes.
|
||||
int graph_cpynode_index = -1;
|
||||
#endif
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user