add PULL_REQUEST_TEMPLATE.md and ISSUE_TEMPLATE

Signed-off-by: tanjunchen <tanjunchen20@gmail.com>

.github/ISSUE_TEMPLATE/001_feature_request.yaml

@@ -0,0 +1,60 @@
+name: Feature Request
+description: Propose a new feature or enhancement
+labels: ["feature request"]
+title: "feature: <short summary>"
+body:
+  - type: markdown
+    attributes:
+      value: |
+        👋 **Thanks for taking the time to submit a feature request!**
+
+        Please help us understand your idea clearly by filling out the sections below.
+        Well-described proposals are easier to evaluate and more likely to be prioritized.
+
+  - type: textarea
+    attributes:
+      label: Feature Description
+      description: |
+        Describe the feature or enhancement you are proposing.
+        What should it do? What problem does it solve?
+        Please be as clear and specific as possible.
+      placeholder: |
+        Example:
+        - Add support for XXX
+        - Improve performance of YYY under ZZZ workload
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Motivation / Use Case
+      description: |
+        Why do you need this feature?
+        Describe the real-world use case, workload, or scenario where this feature is important.
+      placeholder: |
+        Example:
+        - This feature is required to support large-scale inference
+        - Needed to reduce TTFT/TPOT under high concurrency
+    validations:
+      required: false
+
+  - type: textarea
+    attributes:
+      label: Additional Context
+      description: |
+        Add any additional context that may help us evaluate this request.
+        This can include design ideas, references, benchmarks, logs, or related issues/PRs.
+      placeholder: |
+        - Related issues or PRs
+        - Links to papers or docs
+        - Performance numbers or expected impact
+    validations:
+      required: false
+
+  - type: markdown
+    attributes:
+      value: |
+        👍 **Community feedback matters!**
+
+        If you find this proposal useful, feel free to give it a 👍.
+        We often prioritize feature requests with strong community interest.

.github/ISSUE_TEMPLATE/002_bug_report.yaml

@@ -0,0 +1,74 @@
+name: Bug Report
+description: Report a bug or unexpected behavior
+labels: ["bug"]
+title: "bug: <short summary>"
+body:
+  - type: markdown
+    attributes:
+      value: |
+        🐞 **Thanks for reporting a bug!**
+
+        To help us investigate and fix the issue efficiently, please provide as much
+        relevant information as possible. Clear and reproducible reports are highly appreciated.
+
+  - type: textarea
+    attributes:
+      label: Bug Description
+      description: |
+        Clearly and concisely describe the bug.
+        What happened? What is broken or behaving incorrectly?
+      placeholder: |
+        Example:
+        - vLLM crashes when loading model XXX
+        - Unexpected latency spike during decode stage
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Steps to Reproduce
+      description: |
+        Provide the exact steps to reproduce the issue.
+        Please include commands, configuration, and minimal repro if possible.
+      placeholder: |
+        Example:
+        1. Start vLLM with config XXX
+        2. Send request YYY
+        3. Observe error or incorrect behavior
+    validations:
+      required: true
+
+  - type: textarea
+    attributes:
+      label: Expected Behavior
+      description: |
+        Describe what you expected to happen instead.
+        This helps clarify whether the behavior is incorrect or just unexpected.
+      placeholder: |
+        Example:
+        - Model should load successfully
+        - Latency should remain stable under N requests
+    validations:
+      required: false
+
+  - type: textarea
+    attributes:
+      label: Additional Context
+      description: |
+        Add any additional information that may help diagnose the issue.
+        This can include logs, stack traces, environment details, or related issues.
+      placeholder: |
+        - Logs / stack traces
+        - OS, CUDA, driver, hardware info
+        - vLLM / Kunlun version
+        - Related issues or PRs
+    validations:
+      required: false
+
+  - type: markdown
+    attributes:
+      value: |
+        👍 **Does this bug affect you as well?**
+
+        Please consider giving it a 👍.
+        We often prioritize issues that impact a larger portion of the community.

.github/ISSUE_TEMPLATE/099_config.yml

@@ -0,0 +1,8 @@
+blank_issues_enabled: true
+
+contact_links:
+  - name: 📘 Documentation & Tutorials
+    url: https://vllm-kunlun.readthedocs.io
+    about: |
+      Please check the official documentation and tutorials first.
+      Many common questions, usage examples, and best practices are covered there.

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,85 @@
+## PR Description
+
+<!--
+Please provide a clear and concise description of this PR:
+- What problem does it solve?
+- Why is this change needed?
+- What is the overall approach?
+-->
+
+FIX #xxxx  
+<!-- Link the existing issue(s) this PR resolves, e.g.:
+FIX #1234
+-->
+
+---
+
+## Checklist (Required)
+
+Before submitting this PR, please ensure that all the following items are completed:
+
+- [ ] All code changes pass the [`pre-commit`](https://github.com/baidu/vLLM-Kunlun/blob/main/CONTRIBUTING.md) checks.
+- [ ] Commits are signed off using `git commit -s`.
+- [ ] The PR title is properly classified (see below).
+
+---
+
+## PR Type
+
+Please prefix the PR title with one or more of the following labels to help reviewers quickly understand the nature of the change:
+
+- `[Feature]` – New features or enhancements (e.g. Attention, Communicator, Kernel, Worker, etc.)
+- `[Bugfix]` – Bug fixes
+- `[CI/Build]` – CI, build system, or infrastructure improvements
+- `[Doc]` – Documentation updates or fixes
+- `[Misc]` – Other changes that do not fit the above categories (use sparingly)
+
+> **Note:** If the PR spans multiple categories, include all relevant prefixes.
+
+---
+
+<details>
+<summary><b>Detailed Checklist (Click to Expand)</b></summary>
+
+<p>Thank you for contributing to <b>vLLM Kunlun</b>!  
+To help us maintain high code quality and streamline the review process, please ensure your PR meets the following requirements.</p>
+
+<h3>1. Code Quality</h3>
+
+<ul>
+    <li>All linting and formatting checks pass (<code>pre-commit</code>).</li>
+    <li>The code is well-structured and sufficiently documented.</li>
+    <li>The change is designed with maintainability and readability in mind.</li>
+</ul>
+
+<h3>2. Testing</h3>
+
+<ul>
+    <li>Relevant unit tests are added or updated.</li>
+    <li>Integration tests are included when applicable.</li>
+    <li>Existing tests continue to pass.</li>
+</ul>
+
+<h3>3. DCO Compliance</h3>
+
+<p>This project follows the
+<a href="https://github.com/vllm-project/vllm/blob/main/DCO">Developer Certificate of Origin (DCO)</a>.</p>
+
+<ul>
+    <li>All commits include a <code>Signed-off-by:</code> line.</li>
+    <li>Use <code>git commit -s</code> to automatically add the sign-off.</li>
+</ul>
+
+<h3>4. Review Expectations</h3>
+
+<p>During the review process, maintainers may:</p>
+
+<ul>
+    <li>Request code refactoring or additional tests.</li>
+    <li>Ask for clarifications on design decisions.</li>
+    <li>Suggest performance, stability, or maintainability improvements.</li>
+</ul>
+
+<p>We appreciate your patience and collaboration throughout the review process!</p>
+
+</details>