[Hardware][Intel GPU] Add v1 Intel GPU support with Flash attention backend.

[jikunshang]

Essential Elements of an Effective PR Description Checklist

• [x] The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• [x] The test plan, such as providing test command.
• [x] The test results, such as pasting the results comparison before and after, or e2e results
• [ ] (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

previous PR is #14612 this PR add Intel GPU V1 engine support. This PR includes a. integrates flash_attn_varlen_func kernel(V2) on xpu which is implemented in ipex, b. Refine some xpu related configs c. Support vLLM V1 by adding xpu_worker/xpu_model_runner to handle xpu code path d. Docker file/ dependency updates. e. Add a V1 test in CI.

Test Plan

Add a V1 test in xpu CI. Intel vllm team is also working on UT on xpu fixing. We will upstream in further PRs for ut.

Test Result

I did a quick benchmark on both V0/V1 on PVC 1100. V1 have 1.55x throughput performance boost compare to V0 (3328.59 vs 2139.68). Please be aware both are not fine tuned parameters. command I use:

VLLM_USE_V1=0 python3 benchmarks/benchmark_throughput.py --model meta-llama/Meta-Llama-3-8B-Instruct --dataset benchmarks/ShareGPT_V3_unfiltered_cleaned_split.json  --enforce-eager 
VLLM_USE_V1=1 python3 benchmarks/benchmark_throughput.py --model meta-llama/Meta-Llama-3-8B-Instruct --dataset benchmarks/ShareGPT_V3_unfiltered_cleaned_split.json  --enforce-eager 

(Optional) Documentation Update

[github-actions[bot]]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist[bot]]

[!WARNING] You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[gemini-code-assist[bot]]

[!WARNING] You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[gemini-code-assist[bot]]

[!WARNING] You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[gemini-code-assist[bot]]

[!WARNING] You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @jikunshang.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[xuechendi]

@WoosukKwon , may you review this PR?

[xuechendi]

@simon-mo @WoosukKwon @robertgshaw2-redhat @mgoin , may you take a final review, hope we can merge it soon.

[skyloevil]

lgtm