| 1 | <!-- markdownlint-disable --> |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | <!-- Summarize the change in 1-2 lines. Link relevant issues and PRs. --> |
| 6 | |
| 7 | ## Claims |
| 8 | |
| 9 | <!-- State the accomplishments in a few concrete bullets: speedups, feature support, bug fixes, etc. --> |
| 10 | |
| 11 | ## Validation |
| 12 | |
| 13 | <!-- Show evidence that the claims are met by this change, and steps to reproduce validations. --> |
| 14 | |
| 15 | ## Details |
| 16 | |
| 17 | <!-- Explain motivation, design decisions, root cause, tradeoffs, and limitations concisely. Link or collapse lengthy supporting material. --> |
| 18 | |
| 19 | --- |
| 20 | |
| 21 | <details> |
| 22 | <summary> Pull Request Checklist </summary> |
| 23 | |
| 24 | - [ ] I used vLLM's `/pr-checklist` skill. (Mandatory for agents, optional for humans). |
| 25 | - [ ] AI assistance was used during the creation of this PR. |
| 26 | |
| 27 | - [ ] **Design Fit:** Minimizes impact on core components, reuses existing functionality, and justifies added complexity. |
| 28 | - [ ] **Testing and Validation:** Validates the change and ensures any added tests are meaningful and reliable, with CI coverage or documented CI resource constraints and validation performed outside CI. |
| 29 | - [ ] **Code Quality and Style:** Keeps code and comments clear and concise, and updates relevant documentation and examples. |
| 30 | - [ ] **Pull Request Contents:** Includes a brief summary and relevant links, supports claims with evidence, explains root causes and implementation trade-offs, and follows the contributing guide. |
| 31 | </details> |
| 32 | |
| 33 | **BEFORE SUBMITTING, PLEASE READ <https://docs.vllm.ai/en/latest/contributing>** (anything written below this line will be removed by GitHub Actions) |