github ✓analyzed · update queued (15 behind) ? deep scan unknown sandraschi/diffusion-llm-mcp
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidecar next. Complements local-llm-mcp.
- licence
- MIT
- first seen
- 2026-06-17
- last seen
- 2026-06-17
- releases · 30d
- 0
- short id
-
- new_repo new repo sandraschi/diffusion-llm-mcp 12w
j down k up gg top G end