tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 04:45:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-07-18 23:48:47 +02:00
committed by GitHub
parent 705b7ecf60
commit a15ef8f8a0
4 changed files with 29 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -134,6 +134,10 @@ void ggml_backend_buffer_set_usage(ggml_backend_buffer_t buffer, enum ggml_backe
}
}
enum ggml_backend_buffer_usage ggml_backend_buffer_get_usage(ggml_backend_buffer_t buffer) {
return buffer->usage;
}
ggml_backend_buffer_type_t ggml_backend_buffer_get_type(ggml_backend_buffer_t buffer) {
return buffer->buft;
}