Skip to content

Why are write operations not executed for newly generated tokens in kv-cache.py #351

@ctcommon

Description

@ctcommon
Image

After reading the benchmark code above, I have two questions:
Why does the benchmark not perform write operations for newly generated tokens?
Why does the benchmark simulate reading the KV cache only once when generating multiple tokens in a batch?

Or am I overthinking it — is it that there is no actual model that can do this, and this implementation is just trying to keep the code as simple as possible to maximize testing of storage pressure and performance?

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