diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-01 08:25:27 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-01 08:25:27 +0200 |
| commit | a79ab8f34222e1e0142a30eaa97e78ad077abca9 (patch) | |
| tree | 24f89079780736d697347e1ebbe6544750534e22 /examples/embedding/embedding.cpp | |
| parent | b762db7c9264199c2d0f66e7d63e3b4884f3fc0c (diff) | |
Reduce size of compute buffers (#237)
* This reduces compute buffer size for MLA
* This should accomplish it for standard attention
* Much better
* Better concat for contiguous tensors
If all the op does is to concatenate the second tensor
to the first, why would we want to have a loop?
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/embedding/embedding.cpp')
0 files changed, 0 insertions, 0 deletions