| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | 20241118 docs (#2629) | zachcp | 2024-11-19 | 1 | -0/+1 |
| | | | | | | | | | | | | | | | | | | * module docs * varbuilder gguf docs * add a link to gguf files * small additonal mod doc titles * safetensor docs * more core docs * more module docs in canlde_core * 2 more link fixes | ||||
| * | Metal part 1 - Scaffolding for metal. (#1308) | Nicolas Patry | 2023-11-10 | 1 | -0/+4 |
| | | | | | | * Metal part 1 - Scaffolding for metal. * Remove tracing. | ||||
| * | Q6K quantization (#495) | Laurent Mazare | 2023-08-17 | 1 | -0/+16 |
| | | | | | | | | | | | | | | | | * Print the detected arch options. * Add the q6k quantization. * Add a currently broken test. * Bugfix. * Bugfix. * Another bugfix. * Another bugfix + get the test to work. | ||||
| * | Support the Accelerate BLAS on macOS. (#325) | Laurent Mazare | 2023-08-05 | 1 | -8/+6 |
| | | | | | | * Add the accelerate feature. * Ffi tweaks. | ||||
| * | Add some 'cuda-if-available' helper function. (#172) | Laurent Mazare | 2023-07-15 | 1 | -0/+7 |
| | | |||||
| * | Resurrect the llama npy support. (#140) | Laurent Mazare | 2023-07-11 | 1 | -0/+7 |
| | | |||||
| * | PyTorch like display implementation. | laurent | 2023-06-27 | 1 | -1/+1 |
| | | |||||
| * | Use num-cpus to enable parallelism. | laurent | 2023-06-27 | 1 | -0/+12 |
 |
index : forks/candle.git | |
| summaryrefslogtreecommitdiff |