neuronx-cc compile --framework=XLA model.MODULE_f53407701fa4882a24c0+55c11e15.hlo_module.pb --output model.MODULE_f53407701fa4882a24c0+55c11e15.neff --target=trn2 --auto-cast=none --model-type=transformer '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ' --lnc=2 -O2 --internal-hlo2tensorizer-options=--verify-hlo=true --logfile=log-neuron-cc.txt --verbose=35