optimum-neuron-cache
/
neuronxcc-2.21.18209.0+043b1bf7
/MODULE_0a328344d47093240e2f+77dd30e9
/compile_flags.json
| ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma ", "--lnc=1", "-O2", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk2/log-neuron-cc.txt"] |