| Commit message (Expand) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Handle multiple dimensions in metal QMM + two fixes. (#2097) | Laurent Mazare | 2024-04-20 | 1 | -15/+20 |
| * | Handle the batch dimension in quantized MMV on metal. (#2022) | Laurent Mazare | 2024-04-06 | 1 | -1/+4 |
| * | Improve metal buffer usage (#1807) | ivarflakstad | 2024-03-07 | 1 | -2/+7 |
| * | Cuda acceleration for quantized model. (#1754) | Laurent Mazare | 2024-02-25 | 1 | -35/+18 |
| * | Qmetal tweaks (#1704) | Laurent Mazare | 2024-02-13 | 1 | -9/+86 |
| * | Fixing quantized llama demo on metal. (#1703) | Nicolas Patry | 2024-02-13 | 1 | -0/+4 |
| * | Quantized GGUF style (#1523) | Nicolas Patry | 2024-01-17 | 1 | -0/+153 |
 |
index : forks/candle.git | |
| summaryrefslogtreecommitdiff |