lllyasviel / lllyasviel/FramePack

Does RAM offload work in Linux

Open
#770 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.3k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

Thank you for the excellent work Lvmin Zhang, team and community

4090 Laptop 16GB VRAM

96GB RAM

I'm getting OOM, I tried setting PYTORCH_ALLOC_CONF=expandable_segments:True and Increased GPU Inference Preserved Memory to 16 and still results in OOM.

I see that RAM is not utilized completely, although I see others on Windows complain that its using too much RAM.

Has anyone on Linux successfully generated output using FramePack?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No source file or test is named. Start by reproducing the Linux OOM with the reported 4090 Laptop, 16GB VRAM, 96GB RAM, and PYTORCH_ALLOC_CONF setting, then inspect how FramePack handles RAM offload during inference. Done would require establishing whether RAM offload works on Linux and documenting the relevant result or limitation.

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.