vllm-rocm-pr-reviewlisted

# vLLM ROCm PR Review Review a `vllm-project/vllm` PR through an AMD/ROCm lens, then write a **concise Chinese review report** to `./outputs/pr-<NUMBER>-review.md`. Knowledge sources (kept in `references/`): | File | Content | When to read | |------|---------|--------------| | `references/vllm-rocm-review-rules.md` | Curated rule catalog adapted from the ATOM/aiter review skills to vLLM's ROCm surface | The mandatory checklist (Step 6) | | `references/upstream/atom-review-pr-skill.md` | Full upstream ATOM review-pr skill | Deep reviews / new rule discovery | | `references/upstream/aiter-review-pr-skill.md` | Full upstream aiter review-pr skill | Deep reviews / new rule discovery | | `references/upstream/mori-readme.md` + `mori-structure.json` | mori (AMD comm library) README + repo tree snapshot | PRs touching mori / MORI-EP / moriio | | `references/example-report.md` | A completed Chinese review report as style anchor | Before writing the report | **Context economy**: for quick reviews, read only the rule categories mapped by the PR type (Step 4) plus the core discipline section of the rules file. For deep reviews (Tier-1 backbone files touched, mori changes, perf claims), read the full rules file. ## Workflow 1. Fetch PR data — `scripts/fetch_pr_data.py` 2. ROCm relevance gate 3. Semantic understanding (5 questions) 4. PR-type classification → mandatory rule categories 5. Backbone-file risk assessment 6. Apply the rule checklist 7. AI-code diagnostic + blind-spot chec