-
Notifications
You must be signed in to change notification settings - Fork 504
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
gpu跑paraformer larger onnx模型时候,模型内部出现维度不匹配错误 #1821
Comments
不知道是不是和拼batch有关? |
1. 问题大概率应该是CIF部分的问题(CIF是for循环实现的):
2. 解决
|
可以先等2天,等我们gpu部署发出来 |
请问发布的是c++版本的gpu部署方案吗? |
gpu运行时候,batchsize都是1,有时候gpu能够跑完整个测试集,循环几遍之后,在某次循环上,出现这个问题,具体看了torch整个forward代码,没找可怀疑的地方, 反而感觉是onnxruntime导致显存不安全导致的问题。transpose, view操作导致的 连续显存和非连续显存?我也尝试增加了contiguous,导出模型,偶现的几率变小了,也有可能测试环境的不同??很疑惑 |
是的,在写文档了。 |
gpu跑paraformer larger onnx模型时候,模型内部出现维度不匹配错误
模型使用的是:https://modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx/files
没有量化模型;
错误:
请问,这个和什么有关系?如何更好解决或者定位问题?
其他:使用cpu跑的时候,没有出现问题,gpu会偶发这个问题。
The text was updated successfully, but these errors were encountered: