Commit Graph

3 Commits

Author SHA1 Message Date
783735cf22 Use softmax-last-dim where possible. (#1057) 2023-10-08 13:16:42 +01:00
1fcac4afed Expose a function to clear the KV cache on mixformers. (#964) 2023-09-26 05:41:07 +01:00
0007ae9c11 Add the quantized mixformer model. (#953)
* Add the quantized mixformer model.

* Add the quantized option in the phi example.
2023-09-24 15:03:48 +01:00