vllm-ascend-pd-serving git:20260908.b45d86bC

Immutable. This exact content is served forever at /api/v1/blob/5b0355952f11ff38.

<!-- Generated Claude Code shim from .agents/skills/vllm-ascend-pd-serving/SKILL.md. Do not edit. -->
---
name: vllm-ascend-pd-serving
description: Plan, start, inspect, smoke-test, and stop a multi-session vLLM Ascend prefill/decode deployment with explicit connector configuration, role ordering, proxy endpoint health, rollback, and KV-transfer request evidence. Use for PD disaggregation with NIXL, Mooncake, or another KV connector. Do not use for one colocated service, generic Ray clusters, correctness matrices, performance regression decisions, or distributed root-cause diagnosis.
---

# vLLM Ascend PD Serving

Canonical skill source:

`.agents/skills/vllm-ascend-pd-serving/SKILL.md`

Before using this skill:

1. Read the canonical skill file above.
2. Follow its routing rules, entrypoints, guardrails, and acceptance criteria.
3. Use the remote-dev companion tools (`remote_*` MCP tools; CLI fallback `remote-dev <hyphen-tool> ...` or `uv run remote-dev <hyphen-tool> ...`) for ordinary remote endpoint read/edit/bash/search/patch work.
4. Use this Claude project skill only for the domain workflow described by the canonical source.