neuronx-cc compile --framework=XLA model.MODULE_b3ddbc97e5f0d1d64c82+155de413.hlo_module.pb --output model.MODULE_b3ddbc97e5f0d1d64c82+155de413.neff --target=trn1 --auto-cast=none --model-type=transformer '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ' --lnc=1 -O1 '--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10  --verify-hlo=true' --logfile=log-neuron-cc.txt --verbose=35