mostlygeek/llama-swap v169

on GitHub

This update adds usage tracking for API calls made to POST /upstream/{model}/{api}. Now, chats in the llama-server UI show up in the Activities tab. Any request to this endpoint that includes usage or timing info will appear there (infill, embeddings, etc).

Changelog

• e250e71 Include metrics from upstream chat requests (#361)
• d18dc26 cmd/wol-proxy: tweak logs to show what is causing wake ups (#356)