Simple framework for LLM inferencing

Simple framework for LLM inferencing

LLM::Graph can be used to efficiently schedule and combine multiple LLM generation steps for an optimal evaluation managing LLM submissions' concurrency.

ML::NLPTemplateEngine provides function(s) for making computational workflows.

Native Raku bindings for ONNX Runtime - run ONNX models directly in Raku

WWW::LLaMA provides access to the LLaMA playground.

Different subs and CLI scripts for specific but repeatable LLM-based workflows.

ML::FindTextualAnswer provides function(s) for finding sub-strings in given text that appear to answer given questions.

Minimal Raku bindings for ONNX Runtime (inference only)

WWW::Gemini provides access to Google's Gemini LLM models.