LLM Configuration
Configure RuVLLM for local inference and fine-tuning.
When to use
When you need to configure local LLM inference, create MicroLoRA adapters for task-specific fine-tuning, or set up SONA for real-time adaptation.
Steps
- Check status — call
mcp__plugin_ruflo-core_ruflo__ruvllm_statusto see current model and adapter state. Ifwasm.availableisfalse, install the add-on first (npm i -g @ruvector/ruvllm-wasm, or without-gin a project) — the MicroLoRA and SONA tools cannot run without it - Generate config — call
mcp__plugin_ruflo-core_ruflo__ruvllm_generate_configwith model parameters - Create MicroLoRA — call
mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_createwithinputDim,outputDim,rank(1-4, default 2) andalpha - Adapt MicroLoRA — call
mcp__plugin_ruflo-core_ruflo__ruvllm_microlora_adaptwithloraIdand aqualitysignal (0.0-1.0), optionallearningRateandsuccess. It takes a feedback score, not a training set - Create SONA — call
mcp__plugin_ruflo-core_ruflo__ruvllm_sona_createwithhiddenDim(default 64),learningRateandpatternCapacity - Adapt SONA — call
mcp__plugin_ruflo-core_ruflo__ruvllm_sona_adaptwithsonaIdand aqualitysignal (0.0-1.0)
MicroLoRA vs SONA
| Feature | MicroLoRA | SONA |
|---|---|---|
| What it is | Ultra-light LoRA adapter, rank 1-4 | Instant adaptation loop (the tool describes <1ms cycles) |
| Input | quality feedback per call |
quality feedback per call |
| Persistence | None: instances live in the MCP server's memory and are lost on restart | None: same |
Neither tool fine-tunes a hosted model or writes adapter files; both adjust small in-process weights from quality scores. Keep the returned loraId / sonaId for later calls, and re-create them after a restart. For the repo's measured SONA latency see docs/reviews/intelligence-system-audit-2026-05-29.md.
