ExLLama (LLama CPP Nif Wrapper v0.4.1)

Copy Markdown

Top-level facade for ExLLama: model loading, session creation, completions, and the native Jev classifier entry points.

Main entry points

Streaming generation is available on sessions via ExLLama.Session.start_completing_with/2, which delivers {:ok, chunk} messages terminated by :fin to the target process.

Summary

Functions

advance_context(session, content)

chat_completion(model, thread, options)

classify(classifier, request, options \\ [])

Execute a validated Core classifier request with a loaded local classifier.

completion(session, max_tokens, stop)

create_session(model)

create_session(model, options)

load_classifier(model_path, head_path, options \\ [])

Load a GGUF Jev backbone and its exported FP32 decision head.

load_model(path)

load_model(path, opts)