Files
candle/candle-transformers
Laurent Mazare 10d47183c0 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.
2024-09-26 10:23:43 +02:00
..
2024-09-26 10:23:43 +02:00
2024-03-02 18:50:01 +01:00

candle-transformers