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

Better CUDA synchronization logic (#2057)

Browse source
This commit is contained in:
Johannes Gäßler 2023-07-01 21:49:44 +02:00 • committed by GitHub
parent befb3a3562
commit 0bc2cdfc87
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 46 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml-cuda.h
View file

@ -8,10 +8,6 @@ extern "C" {
#define GGML_CUDA_MAX_DEVICES 16
struct ggml_tensor_extra_gpu {
void * data_device[GGML_CUDA_MAX_DEVICES]; // 1 pointer for each device for split tensors
};
void ggml_init_cublas(void);
void ggml_cuda_set_tensor_split(const float * tensor_split);