Skip to content

text encoder quantalization support? #352

Description

@Willian7004

You didn't mention specific quantalization support in README. I used https://huggingface.co/unsloth/Qwen2.5-VL-7B-Instruct-GGUF/blob/main/Qwen2.5-VL-7B-Instruct-IQ4_XS.gguf for Qwen Image and it's the first time that I use IQ4_XS quantalization. The text encode got much slower and I got ' Falling back to numpy dequant for qtype: 23 ' in the console. Is it a problem of quantalization supprot?

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