PR #39400: [Doc] Switch K8S examples to default MP mode

• Repository: vllm-project/vllm
• Author: panpan0000
• State: open | merged: False
• Link: https://github.com/vllm-project/vllm/pull/39400

Description (problem / solution / changelog)

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

Fix https://github.com/vllm-project/vllm/issues/38113

per @ed-pai, previous k8s yaml won't work since default docker images has removed ray. so switch the k8s yaml example to default mp(multiprocessing) as distributed backend.

Background:

• since v0.19.0 (per https://github.com/vllm-project/vllm/issues/33445), ray has been removed as default dependency as well as in docker image.
• which breaks lots of ray usage examples using k8s/docker.

This PR preserves the old ray code there as comments, in case some people still need it for reference or pip install ray by themselves.

Also add explicit --distributed-executor-backend ray for examples/online_serving/multi-node-serving.sh

Test Plan

apply the example LWS.md

Test Result

the actual vllm command as below , which aligns https://docs.vllm.ai/en/latest/serving/parallelism_scaling/#running-vllm-with-multiprocessing

cloudshell-worker-npvr4qhxq5:~# kubectl exec -it vllm-0 -- ps -lefww
....  /usr/bin/python3 /usr/local/bin/vllm serve meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline-parallel-size 2 --nnodes 2 --node-rank 0 --master-addr vllm-0.vllm.default --port 8080

cloudshell-worker-npvr4qhxq5:~# kubectl exec -it vllm-0-1 -- ps -lefww
....  /usr/bin/python3 /usr/local/bin/vllm serve meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline-parallel-size 2 --nnodes 2 --node-rank 1 --master-addr vllm-0.vllm.default --headless

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• 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.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing (anything written below this line will be removed by GitHub Actions)

Changed files

• docs/deployment/frameworks/lws.md (modified, +11/-6)
• docs/deployment/integrations/kthena.md (modified, +26/-10)
• examples/online_serving/multi-node-serving.sh (modified, +1/-1)