| Commit message (Expand) | Author | Age | Files | Lines |
* | Fix sigmoid gradient calculation and move sigmoid into a specialized op (#2114) | MilkFather | 2024-04-29 | 1 | -0/+9 |
* | Add support for "sign" on tensors (#2012) | Thomas Santerre | 2024-04-04 | 1 | -0/+9 |
* | Cuda backend optimization (#1886) | Laurent Mazare | 2024-03-20 | 1 | -2/+2 |
* | Fix the silu cuda kernel. (#1710) | Laurent Mazare | 2024-02-14 | 1 | -1/+1 |
* | feat: add silu activation function (#1706) | OlivierDehaene | 2024-02-14 | 1 | -0/+9 |
* | Add the rounding operators. (#1030) | Laurent Mazare | 2023-10-04 | 1 | -0/+12 |
* | Add the missing kernel. (#955) | Laurent Mazare | 2023-09-24 | 1 | -0/+1 |
* | Add an erf based gelu op (#900) | Laurent Mazare | 2023-09-19 | 1 | -0/+17 |
* | Add tanh. (#675) | Laurent Mazare | 2023-08-30 | 1 | -0/+4 |
* | Add the powf op. (#664) | Laurent Mazare | 2023-08-29 | 1 | -0/+4 |
* | Add the recip op + use it in stable-diffusion. (#331) | Laurent Mazare | 2023-08-06 | 1 | -0/+4 |
* | Add some flash attn test (#253) | Laurent Mazare | 2023-07-26 | 1 | -2/+2 |
* | Add the elu cuda kernel. (#114) | Laurent Mazare | 2023-07-10 | 1 | -0/+38 |
* | Tweak the include order to include math.h first. (#100) | Laurent Mazare | 2023-07-07 | 1 | -1/+1 |
* | Include the math.h file to get access to constants. (#99) | Laurent Mazare | 2023-07-07 | 1 | -0/+2 |
* | Minor tweaks. | laurent | 2023-07-03 | 1 | -0/+3 |
* | Add the bf16 cuda kernels. | laurent | 2023-06-29 | 1 | -0/+14 |
* | Add the relu op. | laurent | 2023-06-28 | 1 | -4/+13 |
* | Refactor the hierarchy. | Nicolas Patry | 2023-06-27 | 1 | -0/+69 |