diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2023-08-22 19:41:10 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-08-22 19:41:10 +0100 |
| commit | f9ecc8447753d759e776e762ba9309bb90b76bb3 (patch) | |
| tree | 311d0e2f4dad33ea8174225cc1bfa5bf429ba713 /candle-core/examples/basics.rs | |
| parent | 07067b01dce3c63b45fe4bdeb8d972f279e88b45 (diff) | |
| download | candle-f9ecc8447753d759e776e762ba9309bb90b76bb3.tar.gz candle-f9ecc8447753d759e776e762ba9309bb90b76bb3.tar.bz2 candle-f9ecc8447753d759e776e762ba9309bb90b76bb3.zip | |
GQA support in the quantized model. (#555)
* GQA support in the quantized model.
* Fix the reshaping.
* Fix the main llama model.
* Infer the proper gqa from the model kind.
Diffstat (limited to 'candle-core/examples/basics.rs')
0 files changed, 0 insertions, 0 deletions