tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 08:15:55 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix logic for clearing padding with -ngl 0 (#13320)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-05-05 22:32:13 +02:00
committed by GitHub
parent 233461f812
commit 9070365020
6 changed files with 33 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-backend.cpp
View File

@@ -56,7 +56,7 @@ size_t ggml_backend_buft_get_max_size(ggml_backend_buffer_type_t buft) {
return SIZE_MAX;
}
size_t ggml_backend_buft_get_alloc_size(ggml_backend_buffer_type_t buft, struct ggml_tensor * tensor) {
size_t ggml_backend_buft_get_alloc_size(ggml_backend_buffer_type_t buft, const struct ggml_tensor * tensor) {
// get_alloc_size is optional, defaults to ggml_nbytes
if (buft->iface.get_alloc_size) {
size_t size = buft->iface.get_alloc_size(buft, tensor);
@@ -152,7 +152,7 @@ size_t ggml_backend_buffer_get_max_size(ggml_backend_buffer_t buffer) {
return ggml_backend_buft_get_max_size(ggml_backend_buffer_get_type(buffer));
}
size_t ggml_backend_buffer_get_alloc_size(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor) {
size_t ggml_backend_buffer_get_alloc_size(ggml_backend_buffer_t buffer, const struct ggml_tensor * tensor) {
return ggml_backend_buft_get_alloc_size(ggml_backend_buffer_get_type(buffer), tensor);
}