1
edit
mNo edit summary |
(Correction: virtual env needs to be set up on each node) |
||
Line 592: | Line 592: | ||
module load python # Using Default Python version - Make sure to choose a version that suits your application | module load python # Using Default Python version - Make sure to choose a version that suits your application | ||
srun --tasks-per-node=1 bash << EOF | |||
virtualenv --no-download $SLURM_TMPDIR/env | virtualenv --no-download $SLURM_TMPDIR/env | ||
source $SLURM_TMPDIR/env/bin/activate | source $SLURM_TMPDIR/env/bin/activate | ||
pip install torchvision --no-index | pip install torchvision --no-index | ||
EOF | |||
export NCCL_BLOCKING_WAIT=1 #Set this environment variable if you wish to use the NCCL backend for inter-GPU communication. | export NCCL_BLOCKING_WAIT=1 #Set this environment variable if you wish to use the NCCL backend for inter-GPU communication. |
edit