Skip to content

How to stream model from Disk to VRAM? #7652

Description

@averageaidude

There are a view new models wich need more VRAM than my 72GB VRAM. Does anybody has experience to run a gguf model from nvme? And yes i have a lack of RAM just 32GB. But i remember that llama.ccp can do this and just needs a small buffer for caching. Any idea how to set this up in Oobabooga?

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions