ChatGLM-6B
ChatGLM-6B copied to clipboard
v100 lora fp16训练后有什么推理加速的方法吗
Is there an existing issue for this?
- [X] I have searched the existing issues
Current Behavior
v100 lora fp16训练后有什么推理加速的方法吗
Expected Behavior
No response
Steps To Reproduce
v100 lora fp16训练后有什么推理加速的方法吗
Environment
- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :
Anything else?
No response
+1 希望官方能出一个lora微调后加速推理的方案
+1 同求