vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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;
}