modelscope / modelscope/DiffSynth-Studio
wan2.2-14b 如何用多卡推理？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
2张H20，单卡可以跑推理，但用accelerate launch --multi_gpu --num_processes 2 examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py 跑推理会oom，且nvidia-smi第二张卡一直没看到占用，这个是正确的启动单卡推理的方式吗？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py and the reported accelerate launch --multi_gpu --num_processes 2 command. Check how the entry point initializes devices and run it while observing both H20 cards; done means multi-card inference uses both cards without OOM.
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
- 30/100