tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: mmq CLI option, fixed mmq build issues (#2453)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-07-31 15:44:35 +02:00
committed by GitHub
parent 1215ed7d5c
commit 0728c5a8b9
10 changed files with 67 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-cuda.h
View File

@ -27,6 +27,7 @@ void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
void ggml_cuda_set_main_device(int main_device);
void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
void ggml_cuda_set_scratch_size(size_t scratch_size);
void ggml_cuda_free_scratch(void);
bool ggml_cuda_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);