#!/usr/bin/env bash #export PYTORCH_MIOPEN_SUGGEST_NHWC=1 #export MIOPEN_FIND_MODE=1 export TORCHINDUCTOR_LAYOUT_OPTIMIZATION=1 export PYTORCH_MIOPEN_SUGGEST_NHWC=1 export TORCHINDUCTOR_COORDINATE_DESCENT_TUNING=1 export MIOPEN_PRECISION_FP32_FP32_FP32_TF32_FP32=1 export LD_LIBRARY_PATH=/root/rocblas-install/lib:$LD_LIBRARY_PATH CONFIG=$1 GPUS=$2 NNODES=${NNODES:-1} NODE_RANK=${NODE_RANK:-0} PORT=${PORT:-29500} MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"} PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \ torchrun \ --nnodes=$NNODES \ --node_rank=$NODE_RANK \ --master_addr=$MASTER_ADDR \ --nproc_per_node=$GPUS \ --master_port=$PORT \ $(dirname "$0")/train.py \ $CONFIG \ --seed 0 \ --launcher pytorch ${@:3}