7d ago · llama.cpp releases →
Only run webgpu CI on my fork Add webgpu only workflow Add WebGPU group_norm kernel clean up resolve merge conflicts parameterize data type; clean up cmake…
Includes: llama.cpp b12182, b12183: opencl: add arange (#31829), b12184: llama : add missing link to pthread (#31785), llama.cpp b12185, b12186: vulkan: Add 'readonly' to decodeBuf declarations. (#31833), b12187: webgpu : Implement group norm kernel (#31490)