mirror of https://github.com/hpcaitech/ColossalAI
aibig-modeldata-parallelismdeep-learningdistributed-computingfoundation-modelsheterogeneous-traininghpcinferencelarge-scalemodel-parallelismpipeline-parallelism
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
13 lines
519 B
13 lines
519 B
# distplan in ["colossalai", "pytorch"] |
|
export DISTPAN="colossalai" |
|
|
|
# The following options only valid when DISTPAN="colossalai" |
|
export TPDEGREE=1 |
|
export GPUNUM=4 |
|
export PLACEMENT='cpu' |
|
export USE_SHARD_INIT=False |
|
export BATCH_SIZE=1 |
|
|
|
env OMP_NUM_THREADS=12 colossalai run --nproc_per_node ${GPUNUM} --master_port 29505 train.py \ |
|
--dummy_data=True --tp_degree=${TPDEGREE} --batch_size=${BATCH_SIZE} --plugin='gemini' \ |
|
--placement ${PLACEMENT} --shardinit ${USE_SHARD_INIT} --distplan ${DISTPAN} 2>&1 | tee run.log
|
|
|