Charlene Yang

Results 21 comments of Charlene Yang

[C/PyTorch] Add THD support for cuDNN attention

/te-ci pytorch

[C/PyTorch] Add THD support for cuDNN attention

/te-ci pytorch

[C/PyTorch] Add THD support for cuDNN attention

/te-ci pytorch

[C/PyTorch] Add THD support for cuDNN attention

/te-ci pytorch

[C/PyTorch] Add THD support for cuDNN attention

/te-ci pytorch

[C/PyTorch] Add THD support for cuDNN attention

/te-ci jax

[C/PyTorch] Add THD support for cuDNN attention

/te-ci paddle

[C/PyTorch] Add THD support for cuDNN attention

/te-ci jax

The provided qkv memory layout is not supported! When using RoPE

Hi @1049451037 , could you provide more details about how to run the job please? Currently I can start the job but am stuck at ```building GPT model ... >...

The provided qkv memory layout is not supported! When using RoPE

I tested with TE main (8255f87) and Megatron-LM main (8957468). I'm not seeing the issue above. Let me know if I'm not using the same run script as you have....