Tech News
← Home  ·  All topics

Yarn Truncation

1 GoKawiil brief on this topic · RSS for yarn truncation

ggml library reaches v1.0.0 with API cleanup and cross-backend performance gains

The ggml machine-learning library has released version 1.0.0, removing deprecated public APIs and legacy DIAG_MASK operations while bumping its RPC protocol to block incompatible peers. The release adds configurable YaRN truncation controls, FP8 support, and performance improvements spanning CUDA, Metal, Vulkan, SYCL, OpenCL, WebGPU and Hexagon backends, including new few-row quantized matmuls, MoE fusion, and a smarter scheduler that avoids uploading unused tensor inputs.