[Main][Feat]Set the Profiler parameters through environment variables consistent with vLLM

[zhanghw0354]

What this PR does / why we need it?

Currently, when performing profiling in vLLM-Ascend, if you need to obtain the Python call stack, you have to manually modify the code. The code location is: worker_v1.py#L337 where you set with_stack to true.
Now, in vLLM, you can set whether to obtain the Python call stack through an environment variable. The relevant PR is: #21803 and the documentation is: profiling
This PR sets the profiler initialization parameters by using the same environment variable as vLLM, eliminating the need for manual code modification.

Does this PR introduce any user-facing change?

No

How was this patch tested?

CI passed with new added/existing test.

• vLLM version: v0.10.1.1
• vLLM main: vllm-project/vllm@0235103

[gemini-code-assist]

Code Review

This pull request aligns the profiler configuration in vllm-ascend with the upstream vllm project by allowing with_stack and profile_memory parameters to be set via environment variables. The changes are correct and the tests have been updated accordingly. I've added one high-severity suggestion to use getattr for accessing these new environment variables. This will make the implementation more robust and backward-compatible with older versions of vllm that may not have these variables defined, preventing potential AttributeError exceptions at runtime.

[gemini-code-assist]

To improve robustness and ensure backward compatibility, it's better to use getattr with a default value when accessing these environment variables from envs_vllm. This will prevent an AttributeError if vllm-ascend is run with an older version of vllm where VLLM_TORCH_PROFILER_WITH_STACK or VLLM_TORCH_PROFILER_WITH_PROFILE_MEMORY are not defined. The default value of False will maintain the previous behavior in such cases.

It would also be beneficial to add a new unit test to verify this fallback behavior, ensuring the profiler initializes with with_stack=False and profile_memory=False when the environment variables are not present.

Suggested change

	with_stack=envs_vllm.VLLM_TORCH_PROFILER_WITH_STACK,
	profile_memory=envs_vllm.VLLM_TORCH_PROFILER_WITH_PROFILE_MEMORY,
	with_stack=getattr(envs_vllm, "VLLM_TORCH_PROFILER_WITH_STACK", False),
	profile_memory=getattr(envs_vllm, "VLLM_TORCH_PROFILER_WITH_PROFILE_MEMORY", False),

[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.

[codecov]

Codecov Report

❌ Patch coverage is 80.00000% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 73.50%. Comparing base (fef18b6) to head (79df9e2).
⚠️ Report is 11 commits behind head on main.

Files with missing lines	Patch %	Lines
vllm_ascend/worker/worker_v1.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2608   +/-   ##
=======================================
  Coverage   73.49%   73.50%           
=======================================
  Files         151      151           
  Lines       21927    21929    +2     
=======================================
+ Hits        16116    16118    +2     
  Misses       5811     5811           

Flag	Coverage Δ
unittests	73.50% <80.00%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[zhanghw0354]

@wangxiyuan @Yikun Please review when you have time. Thank you!