Open Issues Need Help
View All on GitHubGenai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
AI Summary: Set up MkDocs to create a comprehensive documentation system for the genai-bench project, improving upon the existing single USER_GUIDE.md file. The new documentation should offer better navigation, search functionality, and overall user experience, scaling to accommodate the project's expanding features.
Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
AI Summary: The task is to evaluate the feasibility of changing the time units used in the `genai-bench` project from seconds to milliseconds. This involves assessing the impact on the existing codebase, user experience, and the potential need for an option to select between seconds and milliseconds.
Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
AI Summary: The task is to clarify the ambiguous naming of the `image-to-text` task in the `genai-bench` project's documentation. The current description in the `USER_GUIDE.md` doesn't accurately reflect the task's requirements, which involve both image and text input to generate text. The solution involves updating the documentation to reflect the correct task name, `Image-text-to-text`, aligning with Hugging Face's task description, and potentially adjusting the code or configuration to ensure consistency.
Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.