Change8

b9127

📦 llama-cppView on GitHub →
1 features🔧 1 symbols

Summary

This release introduces an opt-in Adreno xmem F16xF32 GEMM kernel for OpenCL prefill operations and updates kernel naming conventions. Numerous pre-compiled binaries are provided across multiple operating systems and hardware configurations.

✨ New Features

  • Added opt-in Adreno xmem F16xF32 GEMM support for prefill operations in OpenCL backend.

Affected Symbols