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
segmentation fault illegal instruction #71
Comments
which CUDA version are you using? |
cuda 10.0 |
can you try to uninstall |
Thanks, I try that. |
Still not working. |
@safooray, any ideas here? did you run into similar issues? |
Can you make sure that Also, the binaries we have are for torch==1.2.0. Can you try that instead of 1.4.0? |
Sorry for reply later. |
Another suggestion; can you try running it from inside the docker container that we use to compile the cuda kernel? I am curious, what are you using it for, and would the |
Thanks the suggestion, I try it. I am going to do the research about using TVM or AutoTVM improve the Transformer inference time. When I look out the github, I found your repo is excellent and worth to study. |
Very interesting. Maybe a fused self-attention function or something. I will be curious to see how this goes. Depending on how familiar you are with TVM, you might find the following discussions useful, |
Thanks : ) |
Closing. Please feel free to reopen if needed. |
setup
ubuntu 16.04
tvm 0.7 dev1
pytorch 1.4.0
transformer 2.11.0
other same as requirements.txt
issue
I uncomment the line in diagonaled_mm_tvm.py
DiagonaledMM._get_function('float32', 'cuda')
After that, When I run the code , it show
Loading tvm binary from :./longformer/lib/lib_diagonaled_mm_float32_cuda.so
...
segmentation fault (core dump)
or show
Loading tvm binary from :./longformer/lib/lib_diagonaled_mm_float32_cuda.so
...
illegal instruction (core dump)
other
I test the tvm, tensorflow and pytorch, there are fine.
And I follow the scripts/cheatsheet.txt to regenerate the lib_diagonaled_mm_float32_cuda.so, it can generate succeed.
Any idea or suggestion?
the code is below
The text was updated successfully, but these errors were encountered: