github analyzed · update queued (15 behind) deep scan unknown

sandraschi/diffusion-llm-mcp

github

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.

maintainer
sandraschi
licence
MIT
first seen
2026-06-17
last seen
2026-06-17
releases · 30d
0
short id
activity 1 · times UTC
  • new_repo new repo sandraschi/diffusion-llm-mcp 12w
j down k up gg top G end