Packages

Native Erlang/OTP wrapper around llama.cpp with token-exact tiered KV cache; cache more warm state than fits in RAM

Retired package: Renamed - Renamed to barrel_inference: https://github.com/barrel-platform/barrel_inference

Current section

Files

Jump to
erllama c_src llama.cpp cmake x64-windows-llvm.cmake
Raw

c_src/llama.cpp/cmake/x64-windows-llvm.cmake

set( CMAKE_SYSTEM_NAME Windows )
set( CMAKE_SYSTEM_PROCESSOR x86_64 )
set( CMAKE_C_COMPILER clang )
set( CMAKE_CXX_COMPILER clang++ )