Skip to content

Questions about Table 3 #1

Description

@Zhenyu001225

Congratulations on the MLSys acceptance! I really enjoyed reading your paper and found the Match–Amend–Complete idea very interesting.

I have a question about Table 3: End-to-end Attention Latency. In the table, Quest and RocketKV appear to have higher latency than the FlashInfer full-attention baseline, even under very small KV budgets. This is an important and interesting result, and I would like to better understand the measurement setup.

Would it be possible to share the code or scripts used to reproduce the latency results in Table 3, especially the Quest-related evaluation? I am particularly interested in:

  1. How the end-to-end attention latency was measured.
  2. Whether the reported latency includes the full Quest pipeline, such as page/token selection, metadata processing, KV gathering, and the final attention computation?
  3. Whether the Quest implementation was based on the official repository and whether any modifications were made to integrate it with SGLang / FlashInfer?

Understanding this would be very helpful for interpreting the system-level comparison in Table 3.

Thanks a lot, and congratulations again on the great work!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions