[Docs] Feedback for `/en/latest/contributing/profiling/`

[cyk2018]

📚 The doc issue

When I follow this doc and run OpenAI Server¶, I found

usage: vllm [-h] [-v] {chat,complete,serve,bench,collect-env,run-batch} ...
vllm: error: unrecognized arguments: --profiler-config {"profiler": "torch", "torch_profiler_dir": "/workspace/vllm_profile"}

I want to know if this update in the newer version?

Suggest a potential alternative/fix

No response

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[DarkLight1337]

Can you show your full command?

[cyk2018]

Can you show your full command?

I think like the command in doc, with my model.
vllm serve meta-llama/Llama-3.1-8B-Instruct --profiler-config '{"profiler": "torch", "torch_profiler_dir": "./vllm_profile"}'

[DarkLight1337]

Which version of vLLM are you using? I think this should be supported on v0.13.0 onwards

[cyk2018]

Which version of vLLM are you using? I think this should be supported on v0.13.0 onwards

Great! I found my compile version is v0.12.1, And I will check the update log. Thank you for your reply!

[cyk2018]

Which version of vLLM are you using? I think this should be supported on v0.13.0 onwards

I found no information in the release note, so if it is OK can you give the PR link?