LocalAI Watch posted an update
LocalAI added contextsize to /v1/models/capabilities, making a model’s context-window setting available through the capabilities response.
Why it mattersThe same window also included vLLM-C++ LoRA fusion work and llama.cpp dependency updates.
Discuss: What tooling or client behavior would you want to build around context_size being available in the capabilities response?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.