Expose halo's [fast] MoE preset through the LiteLLM gateway and make it the rag CLI's default chat model (overridable via RAG_CHAT_MODEL), so query synthesis is quicker than the larger coder model. |
||
|---|---|---|
| .. | ||
| aarch64-darwin | ||
| aarch64-linux | ||
| x86_64-darwin/mpro | ||
| x86_64-linux | ||
| nixbuild.nix | ||