nyo16/llama_cpp_ex

Elixir bindings for llama.cpp — run LLMs locally with Metal, CUDA, Vulkan, or CPU. Streaming, chat templates, embeddings, structured output, and concurrent batched inference.

语言：Elixir · GitHub 星标：9 · Fork：2

话题：cuda · elixir · llamacpp · llm

在 GitHub 上查看原仓库