vfdff commented on issue #17984:
URL: https://github.com/apache/tvm/issues/17984#issuecomment-2890057290

   I try to use **tvm 0.18** to check this issue, and It has similar report.
   ```
   export PYTHONPATH=/home/zhongyunde/tvm_codes/tvm-v0.18/python
   ./scripts/2_1_0-experiment_dynamic_dense_ansor_baseline.sh
   ```
   and the above  **tvm 0.18** is configured as following on current gpu 
machine (83, -p 32689)
   ```
   echo "set(USE_CUDA ON)" >> config.cmake
   echo "set(USE_LLVM ON)" >> config.cmake
   echo "set(CMAKE_CUDA_ARCHITECTURES 89)" >> config.cmake
   
   echo "set(CMAKE_BUILD_TYPE Debug)" >> config.cmake
   echo "set(USE_RELAY_DEBUG ON)" >> config.cmake
   ``` 
   
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to