Adds: AMD hipLaunch kernels to the is_cuda_op function

[rohitdwivedula]

See #128 for context.

[github-actions]

MLCommons CLA bot:
Thank you very much for your submission, we really appreciate it. Before we can accept your contribution, we ask that you sign the MLCommons CLA (Apache 2). Please use this [Google form] (https://forms.gle/Ew1KkBVpyeJDuRw67) to initiate authorization. If you are from an MLCommons member organization, we will request that you be added to the CLA. If you are not from a member organization, we will email you a CLA to sign. For any questions, please contact [email protected].
0 out of 1 committers have signed the MLCommons CLA.
❌ @Rohit Dwivedula
Rohit Dwivedula seems not to be a GitHub user. You need a GitHub account after you become MLCommons member. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You can retrigger this bot by commenting recheck in this Pull Request}

[TaekyungHeo]

Thanks for the PR, @rohitdwivedula. First, please sign the CLA to contribute to the Chakra project. Second, I agree that the Chakra toolchains support AMD GPUs. However, the current changes are not ideal. For example, you are introducing AMD GPU keywords in is_cuda_launch_op. We need to better organize our code for generality. Moreover, there are some pending PRs to be merged. It will save your time if you can rebase your PR after the other PRs are merged.

• Add stream ID to GPU operators and support multiple streams in simulate_execution
• Add detailed docstrings to TraceLinker methods and refactor code
• Extract get_inter_thread_dep method to simplify link_ops
• Remove try-except to ensure trace_link stops on exception
• Add missing keyword in is_cuda_launch_op
• Refactor KinetoOperator and TraceLinker for code quality and test coverage

Lastly, please follow the PR template and provide a proper test plan to demonstrate that this PR supports Chakra traces collected from AMD GPUs.