add cuda graph capture failure possible solution

[zhyncs]

Motivation

When using EAGLE 2 speculative decoding, it may fail to start up due to a CUDA graph capture failure. Consider reducing the CUDA graph max batch size (default is 160).

Modifications

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.

[zhyncs]

fix #3395