Motivation

When we run benchmark/mtbench/bench_sglang_eagle.py, this will use the /generate API by default, however, it does not work well for models which require chat APIs such as Llama4, as a result, the acceptance length is extremely low for these models.

Thus, I updated this part of code for two purposes:

1. enable chat api in SGLang frontend
2. enable speculative decoding stats for chat api

Modifications

The results seem good.

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.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.