diff options
| author | Shouzheng Liu <61452103+lshzh-ww@users.noreply.github.com> | 2023-07-12 16:10:55 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-07-12 23:10:55 +0300 |
| commit | 1cbf561466e957b25f0e8163c2386683f8674369 (patch) | |
| tree | 4d796b3189de81bd3a32dde500d1d2f46d06eb07 /examples/server | |
| parent | 975221e9548ef6d9f4af8d39cdffc4811c050beb (diff) | |
metal : new q4_0 matrix-vector kernel (#2188)
Prefetch data to improve GPU utilization. ~48% faster for 33B model.
Diffstat (limited to 'examples/server')
0 files changed, 0 insertions, 0 deletions