Revert "[BugFix] Support setting tp=1 for the Eagle draft model to ta…

[zhaomingyu13]

…ke effect (#5519)"

This reverts commit d886b81.

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.13.0
• vLLM main: vllm-project/vllm@bde38c1

[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.

[gemini-code-assist]

Code Review

This pull request successfully reverts the changes introduced by commit d886b81971f85efcda053e95daa58619f9b1769b. The changes correctly remove the draft_tensor_parallel_size parameter from various test functions and their corresponding speculative_config dictionaries. Additionally, the specific logic for handling tp=1 for the Eagle draft model, including the tp_group_context and its helper function, has been removed from vllm_ascend/spec_decode/eagle_proposer.py and vllm_ascend/worker/model_runner_v1.py. Associated unused imports and minor code simplifications are also part of this revert. The revert appears to be complete and correctly implemented, restoring the codebase to its state before the original bug fix attempt.