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 /llama.h | |
parent | 1215ed7d5ccf854a55eccb52661427bb985e7f2c (diff) |
CUDA: mmq CLI option, fixed mmq build issues (#2453)
Diffstat (limited to 'llama.h')
-rw-r--r-- | llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -108,6 +108,7 @@ extern "C" { // Keep the booleans together to avoid misalignment during copy-by-value. bool low_vram; // if true, reduce VRAM usage at the cost of performance + bool mul_mat_q; // if true, use experimental mul_mat_q kernels bool f16_kv; // use fp16 for KV cache bool logits_all; // the llama_eval() call computes all logits, not just the last one bool vocab_only; // only load the vocabulary, no weights |