罗辑
lightgbm.basic.LightGBMError: bin size 407 cannot run on GPU
> lightgbm.basic.LightGBMError: bin size 407 cannot run on GPU this is a bug for lightGBM run on GPU,when use CPU,it is OK. SO ,LGBM on GPU need improve.
this is a bug for lightGBM for GPU,when use CPU,it is OK.
still have the problem. RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information: python -m bitsandbytes Inspect the output of the command...
> @hellozmz pip install paddlepaddle-gpu 确实，这个解决了问题。paddlepaddle和paddlepaddle-gpu两个可以同时安装
>>> import xmnlp >>> text = "不能适应体育专业选拔人材的要求" File "", line 1 text = "不能适应体育专业选拔人材的要求" IndentationError: unexpected indent >>> text = "不能适应体育专业选拔人材的要求" >>> print(xmnlp.checker(text)) (Lazy Load) Loading model... start to build...
> 我的报这个错误 TypeError: 'NoneType' object is not subscriptable
yes，Facing the same issue, pip install ultralytics==8.0.0 ，then solved。
我们部署到V100后也发现推理巨慢，4B模型，推理一张要20秒，还在找原因中，太慢了。