matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 16:57:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

update llama.cpp

Browse Source
This commit is contained in:
Michael Yang
2023-08-01 16:22:03 -07:00
parent da52f5bfdd
commit 7a1c3e62dc
18 changed files with 2603 additions and 493 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
llama/ggml-cuda.h
View File

@@ -1,5 +1,5 @@
/**
* llama.cpp - git d91f3f0c55663719ea03b76311e8c36ed55eb0e2
* llama.cpp - git c574bddb368424b5996cbee2ec45ec050967d404
*
* MIT License
*
@@ -53,6 +53,7 @@ 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);