summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/with_tracing.rs
Commit message (Expand)AuthorAgeFilesLines
* Use the faster rms-norm kernel for llama. (#2107)Laurent Mazare2024-04-221-0/+5
* Use a common with_tracing::RmsNorm in a few models. (#1871)Jani Monoses2024-03-181-0/+21
* Expose some helper functions to create quantized models. (#1837)Laurent Mazare2024-03-121-0/+6
* Support for attention bias in gemma + refactor things a bit. (#1744)Laurent Mazare2024-02-221-0/+6
* Share the layer-norm implementation. (#1248)Laurent Mazare2023-11-031-0/+31
* Marian MT model (#1210)Laurent Mazare2023-10-291-0/+7
* Remove the unused pragma and properly apply the bias. (#1147)Laurent Mazare2023-10-221-0/+8
* Add the blip image captioning model (#1140)Laurent Mazare2023-10-201-2/+2
* Make some model cloneable. (#1125)Laurent Mazare2023-10-181-3/+4
* Improve the quantized whisper setup. (#1018)Laurent Mazare2023-10-021-1/+1
* Add the quantized mixformer model. (#953)Laurent Mazare2023-09-241-0/+32
* Tracing for the phi model (#936)Laurent Mazare2023-09-231-0/+78
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-13 12:42:12 +0000