Skip to content

Eval bug: suboptimal DFlash multi-slot performance #46

@Anbeeld

Description

@Anbeeld

Name and Version

v0.3.0

Operating systems

Windows

GGML backends

CUDA

Hardware

RTX 3090

Models

No response

Problem description & steps to reproduce

Low tok/s and GPU utilization (70-80%), meaning significant bottlenecks are in place

First Bad Commit

No response

Relevant log output

Logs

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