[Hardware][Intel CPU][DOC] Update docs for CPU backend

[zhouyuan]

This patch adds the typical deployment considerations for vLLM with CPU backend, since it's different with the GPU backend.

related #3654

https://vllm--6212.org.readthedocs.build/en/6212/

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

PR Checklist (Click to Expand)

Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Model] for adding a new model or improving an existing model. Model name should appear in the title.
• [Frontend] For changes on the vLLM frontend (e.g., OpenAI API server, LLM class, etc.)
• [Kernel] for changes affecting CUDA kernels or other compute kernels.
• [Core] for changes in the core vLLM logic (e.g., LLMEngine, AsyncLLMEngine, Scheduler, etc.)
• [Hardware][Vendor] for hardware-specific changes. Vendor name should appear in the prefix (e.g., [Hardware][AMD]).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• We adhere to Google Python style guide and Google C++ style guide.
• Pass all linter checks. Please use format.sh to format your code.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Include sufficient tests to ensure the project to stay correct and robust. This includes both unit tests and integration tests.
• Please add documentation to docs/source/ if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.

Notes for Large Changes

Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with rfc-required and might not go through the PR.

What to Expect for the Reviews

The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:

• After the PR is submitted, the PR will be assigned to a reviewer. Every reviewer will pick up the PRs based on their expertise and availability.
• After the PR is assigned, the reviewer will provide status update every 2-3 days. If the PR is not reviewed within 7 days, please feel free to ping the reviewer or the vLLM team.
• After the review, the reviewer will put an action-required label on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.
• Please respond to all comments within a reasonable time frame. If a comment isn't clear or you disagree with a suggestion, feel free to ask for clarification or discuss the suggestion.

Thank You

Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!

[rafvasq]

Just wanted to offer some proofreading for grammar and readability :)

[zhouyuan]

Hi @WoosukKwon I have made updates to the CPU documentation to reflect the recent changes. Could you please review these diff?

thanks, -yuan

[zhouyuan]

Hi @DarkLight1337 @Isotr0py

Could you please kindly help to take a look on this? This diff is pure for CPU backend doc update.

thanks, -yuan

[Isotr0py]

I'm fine with the cpu-installation part of this doc update. Thanks for updating documentation about new feature on CPU backend!

Let's see if others can have a look on nginx server part. (I'm not familiar with the nginx server deployment)

[DarkLight1337]

(I'm not familiar with the nginx server deployment)

@simon-mo do you know anyone who can review this?

[zhouyuan]

Thank you! @Isotr0py @DarkLight1337

Let's see if others can have a look on nginx server part. (I'm not familiar with the nginx server deployment)

The intention here is to make one example for multiple instances base deployment: e.g., a load-balancer in the front + several vLLM serving endpoints. It is indeed not bounded to CPU backend. Not sure where is the best place to put this part. I'm OK to move this to somewhere else.

thanks, -yuan

[Isotr0py]

Not sure where is the best place to put this part. I'm OK to move this to somewhere else.

Seems that the Nginx Loadbalancer part is put to Getting Started chapter. I think we can move it to Serving chapter just like deploying with k8s and deploying with docker, renaming to deploying nginx loadbalancer.

[Isotr0py]

I can deploy the nginx server following the nginx server instructions, so I'm fine with this part now. Just leave some minor nits.

[zhouyuan]

@Isotr0py @simon-mo Thank you for the review. The failures in CI seems not related with this patch. I'm not able to re-trigger it without modifying the patch, Could you please kindly help here to re-trigger it?

thanks, -yuan

[simon-mo]

Hmmm please can you edit the documentation with gpu example? That's the primary reader's use case

[zhouyuan]

Hmmm please can you edit the documentation with gpu example? That's the primary reader's use case

Hi Simon, make sense, I will modify to use GPU docker as the example.

thanks, -yuan

[zhouyuan]

Hi @simon-mo, gentle ping, I modified the example in Nginx to use GPU docker, could you please check?
85d0ea0

thanks, -yuan