search

ROCm / pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration
http://pytorch.org
Other
219 stars 51 forks source link

[release/2.4] [ROCM] Properly disable Flash Attention/Efficient Attention with environment variables #1570

Closed xinyazhang closed 3 weeks ago

xinyazhang commented 1 month ago

Now USE_FLASH_ATTENTION=0 USE_MEM_EFF_ATTENTION=0 python setup.py can compile correctly.

This is cherry-picked version of https://github.com/pytorch/pytorch/pull/133866