D2D

GGitHub[Doc][skill] Rework main2main skill and add deterministic automation scripts (#9232)

daba6831创建于 9 天前历史提交

文件	最后提交记录	最后更新时间
main2main	[Doc][skill] Rework main2main skill and add deterministic automation scripts (#9232) ### What this PR does / why we need it? This PR reworks the main2main skill into a structured, script-driven pipeline for keeping vLLM-Ascend aligned with upstream vLLM main. It follows the direction in RFC #7074: make main2main caller-agnostic, script-deterministic, incremental, CI-gated, and bounded. The skill now separates high-level agent guidance from deterministic helper scripts and detailed reference material. New structure: ```text main2main/ ├── SKILL.md │ └── Compact entrypoint: guardrails, workflow overview, and pre-completion checklist. ├── scripts/ │ ├── detect_commits.py │ │ └── Initialize workspace and detect base/target vLLM commits. │ ├── plan_steps.py │ │ └── Deterministic step planner for bounded upstream commit ranges. │ ├── step-planner.yaml │ │ └── Classification, weight, and budget configuration for step planning. │ ├── check_and_commit.py │ │ └── Validate commit paths and create signed commits only after CI passes. │ └── run_main2main_ci.py │ └── Run CI and extract structured log summaries. └── reference/ ├── adapt-guide.md │ └── Detailed method for the Adapt phase. ├── diagnosis-guide.md │ └── Detailed method for the Fix-CI loop. ├── final-summary.md │ └── Final reviewer-facing summary template. └── error-pattern-examples.md └── Concrete examples for common CI error fixes. ``` Key workflow changes: - Splits upstream vLLM commit drift into bounded steps before adaptation. - Updates the pinned vLLM commit reference per step. - Requires CI verification for every step, including no-op adapt steps. - Uses structured CI log summaries instead of reading raw logs into agent context. - Commits only after CI passes or only environment flakes remain. - Stops cleanly on bounded fix-loop failure by saving patch and failure summary instead of silently skipping failed steps. - This reduces manual main2main maintenance by making repeatable operations deterministic and keeping the agent focused on the hard parts: understanding upstream API changes, adapting vLLM-Ascend code, and diagnosing CI failures. Reference: [#7074](https://github.com/vllm-project/vllm-ascend/issues/7074) ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.20.2 - vLLM main: https://github.com/vllm-project/vllm/commit/0d4d334eaa583b9c09aa4eb7538c22db99fd84b3 --------- Signed-off-by: Meihan-chen <zr010426ztt@outlook.com>	9 天前
vllm-ascend-model-adapter	[Doc][Misc] Refactor skill documentation and add Claude support instructions (#6817) ### What this PR does / why we need it? This PR refactors the documentation for vLLM Ascend skills. - It renames and moves the vllm-ascend-model-adapter skill's README to serve as a new top-level README for the .agents directory. - It adds instructions on how to use the Ascend skills with Claude, including a new README in the .claude directory. - It updates .gitignore to exclude skills copied for Claude's use. - Add main2main skill This improves the documentation structure, making it more organized and providing clear instructions for developers using these skills with different tools. ### Does this PR introduce _any_ user-facing change? No, this PR contains only documentation and repository configuration changes. It does not affect any user-facing code functionality. ### How was this patch tested? These changes are documentation-only and do not require specific testing. The correctness of the instructions is being verified through this review. - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/83b47f67b1dfad505606070ae4d9f83e50ad4ebd --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>	2 个月前
vllm-ascend-release	[Feature] Add end-to-end release management skill (#6971) ## Summary Related to https://github.com/vllm-project/vllm-ascend/issues/7093. Add vllm-ascend-release skill for automating the end-to-end release process, including: - **Release checklist creation**: Automatically create "[Release]: Release checklist for vX.X.X" issues following the template from #6149 - **Bug triage**: Scan open bugs and prioritize them (P0-P3) based on severity keywords, labels, and user engagement - **Functional testing**: Run automated tests on representative models covering core functionalities: - Qwen3-8B (dense LLM) - Qwen3-MoE-7B (expert parallelism) - Qwen3-VL-7B (multimodal) - DeepSeek-V3 (speculative decoding/MTP) - **Release notes integration**: Invoke the existing vllm-ascend-release-note-writer skill - **Version updates**: Update version references across documentation files - **Announcement generation**: Generate release announcements in multiple formats (GitHub, social media, Chinese) ## Files Added ``` .agents/skills/vllm-ascend-release/ ├── SKILL.md # Main skill documentation ├── templates/ │ ├── release-checklist-template.md # Issue template for release checklist │ └── feedback-issue-template.md # Issue template for community feedback ├── scripts/ │ ├── generate_checklist.py # Generate release checklist from template │ ├── scan_release_bugs.py # Identify release-blocking bugs │ ├── run_functional_tests.py # Run automated functional tests │ ├── update_checklist_section.py # Update sections in checklist issue │ ├── update_version_references.py # Update version in documentation │ └── generate_announcement.py # Generate release announcements └── references/ ├── test-models.yaml # Representative model configurations └── version-files.yaml # Files that need version updates ``` ## Test plan - [ ] Verify skill can be invoked via Claude Code - [ ] Test generate_checklist.py with sample version - [ ] Test scan_release_bugs.py against the repository - [ ] Review test-models.yaml for model coverage 🤖 Generated with [Claude Code](https://claude.com/claude-code) - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7 --------- Signed-off-by: gcanlin <canlinguosdu@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Meihan-chen <jcccx.cmh@gmail.com>	1 个月前