diff options
| author | snadampal <87143774+snadampal@users.noreply.github.com> | 2024-01-26 11:17:59 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-26 19:17:59 +0200 |
| commit | 7032f4f6349c17a8352f9f93f7d2122f45469e59 (patch) | |
| tree | a46a86b55b9bd975fc60e8784da74b8ad64c18a5 /ggml-alloc.c | |
| parent | 5f1925a8cef81eb9b372faaae34b0dd76d5361d4 (diff) | |
ggml : update softmax n_task calculation (#5126)
updated the n_task calculation to use max number of
threads possible. This has improved the prompt eval
performance by around 5% for DOT kernels and by
around 10% for MMLA kernels on AWS Graviton3.
Diffstat (limited to 'ggml-alloc.c')
0 files changed, 0 insertions, 0 deletions