feat: adapt to vLLM main (5af684c3...809b98e5)

[Meihan-chen]

Automated adaptation to upstream vLLM main branch changes.
Commit range: 5af684c31912232e5c89484c2e8259e0fac6c55b...809b98e5b71482e52ee0ecbf140084aae49f3652

phase: detect

round: 0

git_commits:

• sha: 5c84de1566a74e4492347b63de94a81873ecc8b9
  subject: [main2main] Adapt to vLLM commit 809b98e5b
  body:
  Update vLLM commit references from 5af684c3 to 809b98e5b71482e5.

  Upstream changes analyzed between old and new commits:

  • CPU platform refactoring (not affecting NPU platform)
  • MLA prefill backend config additions (new optional fields)
  • MoE activation additions (GELU_TANH) - additive change
  • NaiveAll2AllManager removal - vllm-ascend doesn't use it
  • Eagle CUDA graph manager refactoring - vllm-ascend has own impl

  No code adaptation needed as vllm-ascend doesn't directly depend on
  the removed/changed upstream APIs. Only commit references updated.

  Files changed:

  • .github/workflows/pr_test_light.yaml
  • .github/workflows/pr_test_full.yaml
  • .github/workflows/dockerfiles/Dockerfile.lint
  • docs/source/conf.py

  Co-Authored-By: Claude Opus 4.7 noreply@anthropic.com
  Signed-off-by: main2main-bot main2main-bot@users.noreply.github.com

• vLLM version: v0.19.0

• vLLM main: vllm-project/vllm@5af684c

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.