用 C/C++ 实现的大模型推理引擎，能在普通 CPU 和消费级显卡上跑 LLaMA 等模型，支持量化以降低显存占用。
Prebuilt self-contained binaries for the FunASR llama.cpp / GGUF runtime. This release keeps the default x64 assets conservative for maximum CPU compatibility and adds ex
Full Changelog : https://github.com/Maximilian-Winter/llama-cpp-agent/compare/0.2.34...0.2.35
Full Changelog : https://github.com/Maximilian-Winter/llama-cpp-agent/compare/0.2.33...0.2.34
Full Changelog : https://github.com/Maximilian-Winter/llama-cpp-agent/compare/0.2.32...0.2.33
Full Changelog : https://github.com/Maximilian-Winter/llama-cpp-agent/compare/0.2.31...0.2.32
Full Changelog : https://github.com/Maximilian-Winter/llama-cpp-agent/compare/0.2.30...0.2.31