diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-05-11 12:28:39 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-11 12:28:39 +0200 |
| commit | 9cff7bc3f48bb8836d0f12b22b00baacd7a5c9bb (patch) | |
| tree | f470bc748dcc23bf0306d84184154738b31c63ca /candle-nn | |
| parent | d9bc5ec15164ecb583dbb25653edd89e08e6cbd0 (diff) | |
| download | candle-9cff7bc3f48bb8836d0f12b22b00baacd7a5c9bb.tar.gz candle-9cff7bc3f48bb8836d0f12b22b00baacd7a5c9bb.tar.bz2 candle-9cff7bc3f48bb8836d0f12b22b00baacd7a5c9bb.zip | |
Make it possible to use TF32 accumulation in F32 matmuls. (#2178)
* Allow the use of tf32 accumulation in matmul.
* Better timings.
* Dummy versions for use when cuda is not enabled.
Diffstat (limited to 'candle-nn')
0 files changed, 0 insertions, 0 deletions