inference speed question
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 93
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
你好,
很棒的工作！
想请问这个是正常的生成速度吗？模型是 MOVA-360p，单卡A100。width=352, height=640, offload=cpu
Diffusion: 12%|██████▍ | 6/50 [03:31<23:00, 31.38s/it]
谢谢！
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 reports MOVA-360p inference on a single A100 with CPU offload, at 31.38 seconds per diffusion step. No source file, test, or entry point is named; begin by locating the inference path and reproducing the reported configuration. Done would require establishing whether this speed is expected or identifying a confirmed performance problem.
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
- 20/100