changed examples scripts

Author: williamFalcon

examples/new_project_templates/multi_node_examples/demo_script.sh

@@ -53,6 +53,13 @@ source activate YourEnv
 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=$((12000 + RANDOM % 20000))$
 

examples/new_project_templates/multi_node_examples/minimal_multi_node_demo_script.sh

@@ -10,5 +10,21 @@
 # activate conda 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
 python minimal_multi_node_demo.py