fix bench_speculative bug

[Lzhang-hub]

Motivation

bench_speculative.py has some bug because some args changed in bench_serving.py

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @Lzhang-hub, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a bug in the bench_speculative.py script that arose due to recent argument changes in bench_serving.py. The core purpose of these changes is to ensure the speculative benchmarking script correctly handles both multimodal and non-multimodal models by refactoring how tokenizers and processors are initialized and passed to functions. This also includes updating the benchmarking function calls with new LoRA-related parameters to maintain compatibility and functionality.

Highlights

• Refactored Tokenizer/Processor Handling: The bench_speculative.py script now uses a unified processor object instead of directly passing a tokenizer. This adapts to whether the model is multimodal or not, ensuring the correct instantiation and usage of either an AutoProcessor or AutoTokenizer.
• Multimodal Support Enhancement: Explicitly imports AutoProcessor from transformers and initializes it for multimodal scenarios, ensuring proper handling of multimodal models within the benchmarking script.
• Benchmarking Parameter Alignment: Added lora_request_distribution and lora_zipf_alpha parameters to the benchmark function call, aligning the bench_speculative.py script with recent argument changes introduced in bench_serving.py.
• Type Hinting Improvement: Imported List from the typing module, preparing the script for more robust type hinting.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request fixes a bug in bench_speculative.py that was caused by API changes in bench_serving.py. The changes correctly handle the new processor argument, which can be either a tokenizer or a multimodal processor, and pass the newly required lora_request_distribution and lora_zipf_alpha arguments to the benchmark function. The fix is straightforward and correct. I have no further comments.