llama.cpp
3913f873 - ggml : fix padding in timestep embedding kernels (#15932)

Commit
2 days ago
ggml : fix padding in timestep embedding kernels (#15932) * ggml : remove adding extra dim timestep embedding This commit updates the ggml_timestep_embedding function to no longer add an extra dimension when the specified dimension is odd. The motivation for this change is that this introduces an unnecessary dimension when the dimension is odd, which caused an issue in the kernels which were not expecting this extra dimension and it resulted in uninitialized memory for the second to last dimension. * ggml-cuda : fix padding in timestep embedding kernel This commit removes the zeroing out of the last dimension now that we are not adding the extra padding dimension. * ggml-metal : fix padding in timestep embedding kernel This commit fixes the zero padding for odd dimensions in the timestep embedding kernel * ggml-opencl : fix padding in timestep embedding kernel This commit fixes the zero padding for odd dimensions in the timestep embedding kernel. * ggml-sycl : fix padding in timestep embedding kernel This commit fixes the zero padding for odd dimensions in the timestep embedding kernel. * ggml-vulkan : fix padding in timestep embedding kernel This commit fixes the zero padding for odd dimensions in the timestep embedding kernel. * ggml-cpu : fix padding in timestep embedding function This commit removes the zeroing out of the last dimension now that we are not adding the extra padding dimension.
Author
Parents
Loading