fix: turbomind backend config in cli serve

[PeymanRM]

Motivation

When serving with CLI, arguments: max_prefill_token_num and num_tokens_per_iter weren't being set.

Modification

Added max_prefill_token_num and num_tokens_per_iter as arguments for TurbomindEngineConfig in cli api_serve after being parsed.

Use cases

Taking advantage of "Dynamic SplitFuse"-like behavior using CLI.

Checklist

• Pre-commit or other linting tools are used to fix the potential lint issues.
• The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
• If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
• The documentation has been modified accordingly, like docstring or example tutorials.