3张特斯拉 P40 24G 报错,不加载模型。
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12.3k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
可以进到顺利打开webui。 输入文字后报错。
RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
后台看2张显卡没有任何负载, cudatool 11.6
操作系统 WIn11 + AnaConda,torch 1.13.1+cu116
使用streamlit加载。
streamlit run moss_web_demo_streamlit.py --server.port 8888 -- --model_name fnlp/moss-moon-003-sft --gpu 0,1
--gpu 0,1,2 1,2都试过无用,
Win系统无法运行量化模型。
cuda驱动和gpu信息均正常显示,能运行minigpt-4.说明显卡也无故障。
有谁知道怎么回事吗?
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 moss_web_demo_streamlit.py and reproduce the failure using the reported Streamlit command, Windows 11, Anaconda, torch 1.13.1+cu116, and the fnlp/moss-moon-003-sft model. Check the CUDA device-side assert and GPU-selection behavior for --gpu 0,1 and --gpu 0,1,2; done means the model loads and accepts text without the reported error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- anaconda, python, pytorch, streamlit
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100