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 /examples/common.h | |
| parent | 1215ed7d5ccf854a55eccb52661427bb985e7f2c (diff) | |
CUDA: mmq CLI option, fixed mmq build issues (#2453)
Diffstat (limited to 'examples/common.h')
| -rw-r--r-- | examples/common.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/examples/common.h b/examples/common.h index 1184f32d..97448420 100644 --- a/examples/common.h +++ b/examples/common.h @@ -74,6 +74,7 @@ struct gpt_params { size_t hellaswag_tasks = 400; // number of tasks to use when computing the HellaSwag score bool low_vram = false; // if true, reduce VRAM usage at the cost of performance + bool mul_mat_q = false; // if true, use experimental mul_mat_q kernels bool memory_f16 = true; // use f16 instead of f32 for memory kv bool random_prompt = false; // do not randomize prompt if none provided bool use_color = false; // use color to distinguish generations and inputs |