Rooba
/
lightning
mirror of https://github.com/Lightning-AI/lightning.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

changed examples scripts

This commit is contained in:
William Falcon 2019-09-11 07:03:31 -04:00
parent 30b25c8146
commit cf7dbf6d7c
2 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/new_project_templates/multi_node_examples/demo_script.sh
View File

@ -53,6 +53,13 @@ source activate YourEnv
export NCCL_DEBUG=INFO export NCCL_DEBUG=INFO
export PYTHONFAULTHANDLER=1 export PYTHONFAULTHANDLER=1
# on your cluster you might need these:
# set the network interface
export NCCL_SOCKET_IFNAME=^docker0,lo
# might need the latest cuda
module load NCCL/2.4.7-1-cuda.10.0
# random port between 12k and 20k # random port between 12k and 20k
export MASTER_PORT=$((12000 + RANDOM % 20000))$ export MASTER_PORT=$((12000 + RANDOM % 20000))$

16
examples/new_project_templates/multi_node_examples/minimal_multi_node_demo_script.sh
View File

@ -10,5 +10,21 @@
# activate conda env # activate conda env
conda activate my_env conda activate my_env
# -------------------------
# debugging flags (optional)
# export NCCL_DEBUG=INFO
# export PYTHONFAULTHANDLER=1
# on your cluster you might need these:
# set the network interface
# export NCCL_SOCKET_IFNAME=^docker0,lo
# might need the latest cuda
# module load NCCL/2.4.7-1-cuda.10.0
# -------------------------
# random port between 12k and 20k
export MASTER_PORT=$((12000 + RANDOM % 20000))$
# run script from above # run script from above
python minimal_multi_node_demo.py python minimal_multi_node_demo.py