Mostlylucid.StyloExtract.Llm.LlamaSharp
In-process CPU LLM backend for StyloExtract via LLamaSharp (llama.cpp binding). Loads GGUF models from disk; no Ollama server required. Deployment target: a single ~1-3 GB quantised model embedded in the host process for template-induction / template-repair workloads.
View on Github
Activity
- Latest release
- 2mo ago
- Total releases
- 19
- Cadence
- ~daily
- Last 12 months
- 19
Reach
- Stars
- —
Details
- License
- Unlicense
- First release
- Jun 25, 2026
Releases