Local Ai
b9222
B9222 is a llama.cpp release that adds support for the TRI (Triangle) operation in the Hexagon HTP backend with HVX kernel additions . The release includes optimizations for Hexagon hardware accelerat
B9222 is a llama.cpp release that adds support for the TRI (Triangle) operation in the Hexagon HTP backend with HVX kernel additions . The release includes optimizations for Hexagon hardware accelerators and provides prebuilt binaries for macOS and iOS platforms. Released on May 19, 2026 , this build extends hardware acceleration capabilities for LLM inference across different platforms.
Source: llama.cpp Releases | 2026-05-19