diff options
author | Johannes Gäßler <johannesg@5d6.de> | 2023-07-31 15:44:35 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-31 15:44:35 +0200 |
commit | 0728c5a8b9569183ffca0399caac099afef87595 (patch) | |
tree | 58915b38ddcc28bda0171925548d6b4d6fea2707 /ggml-cuda.h | |
parent | 1215ed7d5ccf854a55eccb52661427bb985e7f2c (diff) |
CUDA: mmq CLI option, fixed mmq build issues (#2453)
Diffstat (limited to 'ggml-cuda.h')
-rw-r--r-- | ggml-cuda.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-cuda.h b/ggml-cuda.h index 3c1e8de..72d7afa 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -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); |