summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/quantized_phi3.rs
Commit message (Expand)AuthorAgeFilesLines
* Documentation Pass for Models (#2617)zachcp2024-11-151-0/+15
* Avoid a contiguous call in the quantized phi 3 model. (#2209)Laurent Mazare2024-05-231-1/+1
* Simplify the KvCache api. (#2207)Laurent Mazare2024-05-231-7/+1
* Support flash-attn in quantized phi3. (#2194)Laurent Mazare2024-05-181-10/+40
* Add a slice_set op. (#2193)Laurent Mazare2024-05-181-22/+19
* Separate quantized phi-3 implementation. (#2157)Laurent Mazare2024-05-041-0/+301