Local Ai
b8953
Release b8953 of llama.cpp adds Q1_0 quantization support for WebGPU, including fast matmul and matvec kernels and optimized shared memory initialization. The release was published on April 28 and inc
Release b8953 of llama.cpp adds Q1_0 quantization support for WebGPU, including fast matmul and matvec kernels and optimized shared memory initialization. The release was published on April 28 and includes pre-built binaries for multiple platforms including macOS, Linux, Android, and Windows with various acceleration backends.
Related
Source: llama.cpp Releases | 2026-04-28