Self-contained C11 CPU inference runtime for GGUF language models, with deterministic decoding, hardened loading, and zero third-party dependencies.
cwindowslinuxofflinetokenizersimdquantizationc11deterministiccpu-inferencellmllm-inferencelocal-aiggufllama-modelsqwen3wayoswayruntime
-
Updated
Aug 30, 2026 - C