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

cuda uma test

Browse source
This commit is contained in:
slaren 2024-05-23 03:13:48 +02:00
parent cd93a28cb1
commit 518b75260b
3 changed files with 68 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-cuda.h
View file

@ -31,6 +31,8 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_typ
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
GGML_CALL ggml_backend_buffer_t ggml_backend_cuda_buffer_from_ptr(int device, void * ptr, size_t size);
GGML_API GGML_CALL int ggml_backend_cuda_get_device_count(void);
GGML_API GGML_CALL void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
GGML_API GGML_CALL void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);