CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Store layers in VRAM

Browse Source
This commit is contained in:
JohannesGaessler
2023-05-09 11:05:58 +02:00
parent d052a0ed4c
commit 3ed4588e22
8 changed files with 74 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ggml.h
View File

@@ -243,6 +243,11 @@ extern "C" {
GGML_TYPE_COUNT,
};
enum ggml_backend {
GGML_BACKEND_CPU = 0,
GGML_BACKEND_CUDA = 1,
};
// model file types
enum ggml_ftype {
GGML_FTYPE_UNKNOWN = -1,
@@ -323,6 +328,7 @@ extern "C" {
// n-dimensional tensor
struct ggml_tensor {
enum ggml_type type;
enum ggml_backend backend;
int n_dims;
int64_t ne[GGML_MAX_DIMS]; // number of elements
@@ -353,7 +359,7 @@ extern "C" {
char name[32];
char padding[8]; // TODO: remove and add padding to name?
char padding[9]; // TODO: remove and add padding to name?
};
// computation graph