Skip to content

[Docs][Feature]add fastdeploy-llm-integration skill & research-report skill#7287

Merged
chang-wenbin merged 2 commits intoPaddlePaddle:developfrom
chang-wenbin:FD_LLM_ADD
Apr 10, 2026
Merged

[Docs][Feature]add fastdeploy-llm-integration skill & research-report skill#7287
chang-wenbin merged 2 commits intoPaddlePaddle:developfrom
chang-wenbin:FD_LLM_ADD

Conversation

@chang-wenbin
Copy link
Copy Markdown
Collaborator

@chang-wenbin chang-wenbin commented Apr 9, 2026

Motivation

为用户提供更好的 Claude Code 使用体验:

  • fastdeploy-llm-integration: 提供完整的 LLM 模型集成指南,降低新模型接入门槛
  • research-report: 支持生成专业的 HTML 研究报告,便于知识沉淀

Modifications

  • 新增 .claude/skills/fastdeploy-llm-integration/ skill,包含:

    • 6 步集成工作流程(架构分析 → 继承策略 → 代码生成 → 注册配置 → 文档 → 测试)
    • 3 种代码模板(继承现有模型、全新 Dense 模型、MoE 模型)
    • 架构选型指南和文档模板
  • 新增 .claude/skills/research-report/ skill,包含:

    • 4 阶段研究流程(明确范围 → 研究 → 生成 HTML → 更新索引)
    • 完整 HTML 模板和样式系统
    • 索引自动更新脚本

Usage

触发 skill 示例:
/skill fastdeploy-llm-integration # 开始新模型集成流程
/skill research-report # 生成研究报告

Accuracy Tests

Checklist

  • Add at least a tag in the PR title.
    • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
    • You can add new tags based on the PR content, but the semantics must be clear.
  • Format your code, run pre-commit before commit.
  • Add unit tests. Please write the reason in this PR if no unit tests.
  • Provide accuracy results.
  • If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

@paddle-bot
Copy link
Copy Markdown

paddle-bot bot commented Apr 9, 2026

Thanks for your contribution!

@chang-wenbin chang-wenbin changed the title [Feature]add fastdeploy-llm-integration skill [Feature]add fastdeploy-llm-integration skill & research-report skill Apr 9, 2026
Copy link
Copy Markdown

@PaddlePaddle-bot PaddlePaddle-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🤖 AI Code Review | 2026-04-09

📋 Review 摘要

PR 概述:新增 fastdeploy-llm-integrationresearch-report 两个 Claude Code skills,用于指导 LLM 模型集成和生成研究 HTML 报告

变更范围.claude/skills/(工具文档目录)

影响面 Tag[Docs]

📝 PR 规范检查

PR 存在以下规范问题:

  1. 描述未填写:PR 描述几乎为空,只保留了模板内容,未填写 MotivationModifications

  2. 标题 Tag 不够准确[Feature] 通常用于新增核心功能,但本 PR 新增的是辅助工具/文档性质的 skills,建议使用 [Docs]

  3. Checklist 未勾选

    • 缺少 pre-commit 运行确认
    • 缺少文档确认

标题建议(可直接复制):

  • [Docs] 添加 fastdeploy-llm-integration 和 research-report skills

描述模板(可直接复制):

## Motivation

为用户提供更好的 Claude Code 使用体验:
- `fastdeploy-llm-integration`: 提供完整的 LLM 模型集成指南,降低新模型接入门槛
- `research-report`: 支持生成专业的 HTML 研究报告,便于知识沉淀

## Modifications

- 新增 `.claude/skills/fastdeploy-llm-integration/` skill,包含:
  - 6 步集成工作流程(架构分析 → 继承策略 → 代码生成 → 注册配置 → 文档 → 测试)
  - 3 种代码模板(继承现有模型、全新 Dense 模型、MoE 模型)
  - 架构选型指南和文档模板
  
- 新增 `.claude/skills/research-report/` skill,包含:
  - 4 阶段研究流程(明确范围 → 研究 → 生成 HTML → 更新索引)
  - 完整 HTML 模板和样式系统
  - 索引自动更新脚本

## Usage

触发 skill 示例:

/skill fastdeploy-llm-integration # 开始新模型集成流程
/skill research-report # 生成研究报告

发现的问题

级别 文件 概述
🟡 建议 PR 规范 描述未填写,Tag 不够准确

总体评价

新增的 2 个 skills 内容质量良好,提供了详细的模板、指南和参考代码,能有效降低用户使用门槛。但 PR 规范需要完善(填写描述、更新 Tag、确认 Checklist)。建议修改后合并。

@codecov-commenter
Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@613f92e). Learn more about missing BASE report.

Additional details and impacted files
@@            Coverage Diff             @@
##             develop    #7287   +/-   ##
==========================================
  Coverage           ?   74.16%           
==========================================
  Files              ?      383           
  Lines              ?    53560           
  Branches           ?     8394           
==========================================
  Hits               ?    39722           
  Misses             ?    11148           
  Partials           ?     2690           
Flag Coverage Δ
GPU 74.16% <ø> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@chang-wenbin chang-wenbin changed the title [Feature]add fastdeploy-llm-integration skill & research-report skill [Docs][Feature]add fastdeploy-llm-integration skill & research-report skill Apr 10, 2026
@chang-wenbin chang-wenbin merged commit 3c54a41 into PaddlePaddle:develop Apr 10, 2026
36 of 38 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants