Agent: llm-action + chitu, lmdeploy, opencode, vLLM

What they did

This recipe groups chitu, lmdeploy, opencode, vLLM because they appear together in registry README cross-links — a signal that maintainers (or the community) treat them as one stack. The anchor repo (chitu) describes: Chitu is a production-grade LLM inference framework supporting NVIDIA, Ascend, Muxi, Hygon and other chips, from single GPU to large cluster deployments Supporting tools: lmdeploy, opencode, vLLM. Install from their runchr pages, then follow the anchor project's docs for orchestration.

How it went

Expect integration work: README links show co-occurrence, not a turnkey tutorial. You should get a coherent stack once each tool is installed and configured per upstream docs.

Worth knowing

Wiring here is inferred from link patterns, not a verified production run. Validate auth, secrets, and model choice on your own repo before relying on it.

Wiring

Inferred from README cross-links between registry tools. Install each tool, then follow the linked README on the primary repo for wiring details.

Try it yourself

Review the anchor README at the source link. List which of these tools (chitu, lmdeploy, opencode, vLLM) you already use, then draft a minimal wiring plan: install order, env vars, and the first end-to-end task you want the stack to perform.