lllyasviel / lllyasviel/FramePack

how can I troubleshoot the blue screen that always appears halfway through the run 请教,每次run执行到中途的时候就总是蓝屏该如何排查?

Open
#210 7 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

请教,每次run执行到中途的时候就总是蓝屏该如何排查?

蓝屏终止代码 MEMORY_ManageMENT

每次差不多执行到Loading checkpoint shards之后就开始蓝屏死机。 无论是完整整合包还是 framepack_cu126_torch26,我怎么能判断错误原因或者哪里查找错误日志?

操作系统 Windows 10 专业版 (64位)
CPU 英特尔 11th Gen Core i7-11700F @ 2.50GHz 八核
主板 华硕 PRIME Z590-P
内存 32GB(2133 MHz / 2133 MHz)
主硬盘 1000 GB (三星 SSD 980 1TB)
显卡 英伟达 NVIDIA GeForce RTX 3060 (12288 MB)
CUDA核心:3584

谢谢,期盼指点回复。

Excuse me, how can I troubleshoot the blue screen that always appears halfway through the run?
Blue screen termination code Memoriy_Managerial
After almost every execution of the Loading Checkpoint Shards, a blue screen crash occurs. How can I determine the cause of the error or where to find the error log, whether it's the complete integration package or framepack_cu126_torch26?
Operating System Windows 10 Professional (64 bit)
CPU Intel 11th Gen Core i7-11700F @ 2.50GHz octa core
Motherboard ASUS PRIME Z590-P
32GB memory (2133 MHz/2133 MHz)
Main hard drive 1000 GB (Samsung SSD 980 1TB)
NVIDIA GeForce RTX 3060 (12288 MB) graphics card
CUDA Core: 3584
Thank you, looking forward to your guidance and reply.

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

Start by reproducing the crash at the reported “Loading checkpoint shards” stage with both the complete integration package and framepack_cu126_torch26. Gather the available error logs or Windows crash information and use the reported MEMORY_MANAGEMENT stop code and hardware details to identify whether the failure is project-specific or environment-related; done means documenting a reproducible cause or actionable diagnosis.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, operating-systems
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.