optimum-neuron-cache
/
neuronxcc-2.21.18209.0+043b1bf7
/MODULE_04a651791e36c2cfd4d1+a9d440f5
/compile_flags.json
| ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] |