[V1] fix torch profiling for V1 offline scenarios

[divakar-amd]

Currently, the torch profiler doesn't capture anything useful for V1 offline benchmarking scenarios as the gpu_worker is attached to a different process.  This PR:

1. Refactors offline benchmarking scripts to capture profiler information for both V0 & V1 mode.
2. Dumps kernels summary table automatically when the profiler is stopped.

• The PR replaces --profile-result-dir and checks if the VLLM_TORCH_PROFILER_DIR environment variable is set before enabling profiling

[github-actions]

👋 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.

🚀