lllyasviel / lllyasviel/FramePack

How to effectively use VRAM

Open
#77 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
17.3k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

It shows 10 GB once I move the slider to 10 but use only 3+ GB. I want to utilize 7 GB to reduce the inference time.
Tried different value like 5, 7 ,....etc but it's only reducing VRAM usage not increasing.

![Image](https://github.com/user-attachments/assets/82048bf2-8b59-40fc-aaaf-0d851512a873)

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names no file, test, or entry point. Start by reproducing the VRAM slider behavior with the reported values and trace how the selected limit affects inference; done means the setting uses the intended VRAM and the inference-time impact is understood or corrected.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.