dist_test.sh 453 Bytes
Newer Older
luopl's avatar
luopl committed
1
2
3
4
5
6
7
8
9
10
11
#!/usr/bin/env bash

CONFIG=$1
CHECKPOINT=$2
GPUS=$3
NNODES=${NNODES:-1}
NODE_RANK=${NODE_RANK:-0}
PORT=${PORT:-29500}
MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"}

PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
dcuai's avatar
dcuai committed
12
torchrun \
luopl's avatar
luopl committed
13
14
15
16
17
18
19
20
21
22
    --nnodes=$NNODES \
    --node_rank=$NODE_RANK \
    --master_addr=$MASTER_ADDR \
    --nproc_per_node=$GPUS \
    --master_port=$PORT \
    $(dirname "$0")/test.py \
    $CONFIG \
    $CHECKPOINT \
    --launcher pytorch \
    ${@:4}