modelscope / modelscope/DiffSynth-Studio
Wan2.1推理速度问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
为什么我用多卡（4卡A100 40G) 推理和单卡推理速度差不多甚至还会更慢呢，有人遇到过这个问题吗？
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
The issue does not name a file, entry point, or test. Start by reproducing Wan2.1 inference with one and four A100 40G GPUs, then inspect the repository's multi-GPU inference path and compare timings. Done means identifying and correcting the cause of multi-GPU inference being no faster or slower than single-GPU inference.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100