| Commit message (Expand) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Flash-Attn upgrade / SoftCap Candle-FlashAttn [1/n] (#2688) | Michael Feil | 2024-12-31 | 1 | -0/+1 |
| * | Update the flash attn kernels. (#2333) | Laurent Mazare | 2024-07-15 | 1 | -1/+17 |
| * | Moving to a proper build crate `bindgen_cuda`. (#1531) | Nicolas Patry | 2024-01-07 | 1 | -239/+34 |
| * | feat: parse Cuda compute cap from env (#1066) | OlivierDehaene | 2023-10-16 | 1 | -36/+52 |
| * | Shape with holes (#770) | Laurent Mazare | 2023-09-08 | 1 | -3/+6 |
| * | Add small customization to the build (#768) | Zsombor | 2023-09-08 | 1 | -4/+20 |
| * | Add back the bf16 flash-attn kernels. (#730) | Laurent Mazare | 2023-09-04 | 1 | -9/+9 |
| * | add c++17 flags (#452) | Chengxu Yang | 2023-08-15 | 1 | -0/+1 |
| * | Add some flash attn test (#253) | Laurent Mazare | 2023-07-26 | 1 | -2/+6 |
| * | Again set a few extra params in flash-attn. (#245) | Laurent Mazare | 2023-07-26 | 1 | -16/+82 |
| * | Specific cache dir for the flash attn build artifacts. (#242) | Laurent Mazare | 2023-07-26 | 1 | -10/+10 |
| * | Add flash attention (#241) | Laurent Mazare | 2023-07-26 | 1 | -0/+182 |
 |
index : forks/candle.git | |
| summaryrefslogtreecommitdiff |