huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-22 12:28:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,342 Commits 74 Branches 16 Tags
783735cf2235877816df01218189bb9c4c4f2ba1
Commit Graph

3 Commits

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