Liger-Kernel icon indicating copy to clipboard operation
Liger-Kernel copied to clipboard

Published 20 hours ago • verified publisher icon linkedin

Modified block and warp sizes for improved performance on XPU for both layernnorm and rmsnorm

Open Tarakarevu1 opened this issue 7 months ago • 0 comments

Summary

This change is related to performance tuning on the Intel Max 1550 GPUs. By keeping the block and warp sizes the same in the forward and backward Triton kernels.

Testing Done

  • Hardware Type: <BLANK>
  • [x] run make test to ensure correctness
  • [x] run make checkstyle to ensure code style
  • [x] run make test-convergence to ensure convergence

Tarakarevu1 avatar Apr 10 '25 05:04 Tarakarevu1