LLM inference engine in plain C/C++ for running large language and vision-language models locally or in the cloud across many hardware backends.
131.8K24.6KC++MITUpdated 10 hours ago
#ggml
Curated GitHub repositories related to ggml, with AI summaries and key stats.
LLM inference engine in plain C/C++ for running large language and vision-language models locally or in the cloud across many hardware backends.