Skip to content

Discrepancy in DFlash baseline numbers compared to original DFlash paper #1

Description

@yulinshih

Thanks for your excellent work!

I noticed some inconsistencies between the DFlash(16) numbers reported in your paper (Table 2) and those reported in the original DFlash paper (Table 1).

For example, for Q3-4B at Temperature=0 on MT-Bench:

  • Your paper reports: Speedup = 2.69×, τ = 5.29
  • DFlash paper reports: Speedup = 2.85×, τ = 4.35

Could the discrepancy in τ be due to a difference in how average acceptance length is computed — for instance, averaging over per-sample acceptance lengths vs. averaging over all individual drafting steps?
Or do you have any other insight into where this gap might come from?

Thank you!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions