CUDA: Error- invalid ptx

[AlexanderKozhevin]

[Artyrm]

I guess maybe it is connected with --fp16 use: triton-lang/triton#187 (comment)
But I can't figure out still how to disable it in this example.

[Artyrm]

Yup.
If you're running ruGPT3XL_generate.ipynb just try to comment out this string in ru_gpts/src/xl_wrapper.py:

    # Fp16 conversion.
    model = FP16_Module(model)

    return model

Like that:

    # Fp16 conversion.
    # model = FP16_Module(model)

    return model

Worked for me.

From my understanding it is because of incompatibility of FP16 with some types of cards, to say Tesla P100 in my case.

UPD looks like I'm wrong - since fp16 work for me with Transformers. DK why it helps.

[king-menin]

Add fixes for last updates on colab for rugpt3xl