llama.cpp
1fe00296 - vulkan: fuse adds (#15252)

Commit
157 days ago
vulkan: fuse adds (#15252) * vulkan: fuse adds Fuse adds that have the same shape, which are common in MoE models. It will currently fuse up to 6 adds, because we assume no more than 8 descriptors per dispatch. But this could be changed. * check runtimeDescriptorArray feature * disable multi_add for Intel due to likely driver bug
Author
Parents
Loading