Fastai support cuda 9.2?

Part 1 (2018)
1

When I run the code below:

learn.precompute=False
learn.fit(1e-2, 3, cycle_len=1)

GPU crashed and computer rebooted. If not run learn.precompute=False ,then learn.fit(1e-2, 3, cycle_len=1) will run normally.
I use my own GPU Titan Xp and Ubuntu 18.04 system and cuda9.2. pytorch 0.4.1 support cuda 9.2.

2

best way to avoid problems like that, is to create fast.ai env using conda. You will have lots of problems like that in future. I have 3 different envs right now (one for Keras, one for Pytorch 0.4.1 and cuda 9.1, one for fast.ai)