-
Luka Govedič authored
[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902) Signed-off-by:luka <luka@neuralmagic.com>
bd56c983
[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass (#10902)
Signed-off-by:
luka <luka@neuralmagic.com>