dbl
dbl
Where is 'FROZEN_SYM_BD' supposed to be declared?
Same issue building 'xformers' from source on MacOS Monterey 12.5.1 ``` (AI-Feynman) davidlaxer@x86_64-apple-darwin13 xformers % MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ pip install -e . Obtaining file:///Users/davidlaxer/xformers Requirement already satisfied: torch>=1.12 in /Users/davidlaxer/anaconda3/envs/AI-Feynman/lib/python3.10/site-packages...
I had to add '-Xclang' to setup.py ``` extra_compile_args["cxx"].append("-Xclang -fopenmp") ```
For --compile=True, will pytorch-20 eventually support AMD GPUs with 'MPS'? (It doesn't work now).
Same issue.
Issues running 'summary.py' on 'MPS' have been reported: https://github.com/openai/tiktoken/issues/47 https://github.com/pytorch/pytorch/issues/92752
Thanks! I'll take a look. https://github.com/allenai/cord19
llama2.c hasn't done much better then nanoGPT: ``` ./run out/model.bin -i "The benefits and the disadvantages of technology-mediated teaching and learning " The benefits and the disadvantages of technology-mediated teaching...
I have tried training on 'mps' on an AMD Radeon Pro 5700XT an A100 on Google Colab Pro. With layers=16 and heads=8 I the loss leveled at ~5 and the...
https://github.com/pytorch/pytorch/issues/113521