Main2main upgrade to vllm 0317 afternoon

[leo-pony]

What this PR does / why we need it?

1.fix "TypeError: get_attn_backend() remove variable": Refactor check_and_update_config

2.fix Rename compile_ranges_split_points to compile_ranges_endpoints

3.fix "RuntimeError: device_allocator not a DeviceAllocator":Replace memory related torch.cuda APIs"

4.fix Support multiple KV groups in OffloadingSpec
removed self.offloaded_block_size and changed self.gpu_block_size from a scalar to a tuple of per-group block sizes, adding block_size_factor.

5.fix Consolidate SupportsEagle renamed
get_eagle3_aux_hidden_state_layers() to get_eagle3_default_aux_hidden_state_layers() and added a supports_eagle3() guard before calling it.

Does this PR introduce any user-facing change?

NA

How was this patch tested?

E2E

• vLLM version: v0.17.0
• vLLM main: vllm-project/vllm@8a68046

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request primarily focuses on upgrading the vllm-ascend project to align with a newer version of vLLM, specifically v0.17.0. The changes involve adapting various components to maintain compatibility with the updated vLLM codebase, including conditional logic for compilation, KV offloading, and attention mechanisms. Additionally, it addresses NPU-specific memory management by patching PyTorch APIs and updates internal documentation to reflect the new version alignment.

Highlights

• vLLM Version Compatibility: Introduced version-dependent logic in ascend_config.py, kv_offload/npu.py, and worker/model_runner_v1.py to handle differences between vLLM versions, specifically targeting v0.17.0 for compilation ranges, KV offloading, and attention backend initialization.
• NPU Memory API Compatibility: Implemented a monkey-patch in platform.py to redirect torch.accelerator memory APIs to their torch.npu equivalents, ensuring proper memory statistics and management for NPU devices.
• Documentation and Metadata Updates: Updated the versioning_policy.md and worker/v2/README.md files to reflect the latest supported vLLM main branch commit hash.
• Test Temporarily Skipped: A specific end-to-end test (test_disaggregated_encoder.py) was temporarily skipped due to an identified issue with EPLB output differences.
• Robustness Improvements: Added hasattr checks in xlite.py before attempting to set deepstack_num_level, mrope_section, and mrope_interleaved attributes, improving code robustness.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Ignored Files

• Ignored by pattern: .github/workflows/** (5)
  • .github/workflows/bot_pr_create.yaml
  • .github/workflows/dockerfiles/Dockerfile.lint
  • .github/workflows/pr_test_full.yaml
  • .github/workflows/pr_test_light.yaml
  • .github/workflows/schedule_codecov_refresh.yaml

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request upgrades vLLM compatibility by introducing version checks and conditional logic to handle API differences. The changes are mostly correct, but I've identified a critical issue where a safety check was removed, potentially causing an AttributeError. I've also pointed out several instances of code duplication that could be refactored to improve maintainability.

Additionally, the pull request title and description do not follow the repository's style guide. I suggest updating them to improve clarity and consistency.

Suggested PR Title:

[main][Misc][Upgrade] Upgrade vLLM compatibility

Suggested PR Summary:

### What this PR does / why we need it?
This PR updates the codebase to be compatible with a newer version of vLLM (commit `8a680463fab3bc9e6760417cd5c0a6aa58283065`). The changes primarily involve:
- Adding version checks and conditional logic to handle API differences in `ascend_config.py`, `kv_offload/npu.py`, and `worker/model_runner_v1.py`.
- Monkey-patching `torch.accelerator` in `platform.py` for NPU compatibility.
- Updating documentation and commit hashes.
- Temporarily skipping a failing test in `test_disaggregated_encoder.py`.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
CI will be used to test the changes.

[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.