diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-09-26 10:23:43 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-09-26 10:23:43 +0200 |
| commit | 10d47183c088ce449da13d74f07171c8106cd6dd (patch) | |
| tree | b91b0398fcb314e998b9f7f3b23877f63462b232 /.github | |
| parent | d01207dbf3fb0ad614e7915c8f5706fbc09902fb (diff) | |
| download | candle-10d47183c088ce449da13d74f07171c8106cd6dd.tar.gz candle-10d47183c088ce449da13d74f07171c8106cd6dd.tar.bz2 candle-10d47183c088ce449da13d74f07171c8106cd6dd.zip | |
Quantized version of flux. (#2500)
* Quantized version of flux.
* More generic sampling.
* Hook the quantized model.
* Use the newly minted gguf file.
* Fix for the quantized model.
* Default to avoid the faster cuda kernels.
Diffstat (limited to '.github')
0 files changed, 0 insertions, 0 deletions