THUDM / ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Other
15.71k stars 1.85k forks source link

[help]请问推理过程中除去模型参数的占用显存,其他部分比如中间矩阵产生的显存占用大约有多大呢? #573

Open zym1599 opened 1 year ago

zym1599 commented 1 year ago

Is there an existing issue for this?

Current Behavior

[help]请问推理过程中除去模型参数的占用显存,其他部分,比如中间矩阵产生的显存占用大约有多大呢?就是推理过程中除了固定的模型权重,其他推理计算需要多大的缓存呢? 谢谢您!

Expected Behavior

No response

Steps To Reproduce

Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :

Anything else?

No response