lllyasviel / lllyasviel/FramePack

FramePack triggers CUDA OOM (>30GB allocation) on 8GB GPU, even with minimal inputs

Open
#271 11 comments 2 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

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 30.26 GiB. GPU 0 has a total capacity of 8.00 GiB of which 3.90 GiB is free. Of the allocated memory 2.62 GiB is allocated by PyTorch, and 446.42 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.

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, test, or entry point is named in the report; start by reproducing the minimal-input run and tracing the CUDA allocation that requests 30.26 GiB. Done should include a confirmed explanation and a regression check or documented hardware requirement for 8GB GPUs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
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.