whchan05
Results
2
issues of
whchan05
It seems that the output of this block is simply reshaped from multiple heads. From the original "Attention is all you need" paper, it seems that there is another linear...
### Describe the issue Title. Once the first pass is complete, subsequent passes can be run faster. Seem to only happen when the device is set to XPU. XPU: CPU:...
XPU/GPU
Performance
Windows