Files
candle/candle-metal-kernels
Laurent Mazare b13a82a438 Separate quantized phi-3 implementation. (#2157)
* Separate quantized phi-3 implementation.

* Integrate the quantized phi3 model.=

* Small fixes, get the generation to work properly.

* Keep the old llama implementation around.

* Change the default.
2024-05-04 10:14:57 +02:00
..
2023-11-30 11:30:31 +01:00
2023-11-20 14:12:56 +01:00

candle-metal-kernels

This crate contains Metal kernels used from candle.