1a1f9a6d89
### What this PR does / why we need it? This PR ports all the deepseek graph mode code and mtp code from v0.7.3 to the main branch --------- Signed-off-by: SidaoY <1024863041@qq.com> Signed-off-by: linfeng-yuan <1102311262@qq.com> Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com> Signed-off-by: mengwei805 <mengwei25@huawei.com> Signed-off-by: libaokui <libaokui@huawei.com> Signed-off-by: q00832892 <qiaoyang19@huawei.com> Signed-off-by: ganyi <pleaplusone.gy@gmail.com> Co-authored-by: SidaoY <1024863041@qq.com> Co-authored-by: linfeng-yuan <1102311262@qq.com> Co-authored-by: Yizhou Liu <liuyizhou5@h-partners.com> Co-authored-by: mengwei805 <mengwei25@huawei.com> Co-authored-by: libaokui <libaokui@huawei.com>
22 lines
566 B
Bash
22 lines
566 B
Bash
export HCCL_IF_IP=${local_ip}
|
|
export GLOO_SOCKET_IFNAME=${ifname}
|
|
export TP_SOCKET_IFNAME=${ifname}
|
|
export HCCL_SOCKET_IFNAME=${ifname}
|
|
|
|
# dp_size = node_size * dp_per_node
|
|
node_size=1
|
|
node_rank=0
|
|
dp_per_node=2
|
|
master_addr=127.0.0.1
|
|
master_port=12345
|
|
|
|
rm -rf ./.torchair_cache/
|
|
rm -rf ./dynamo_*
|
|
rm -rf /root/ascend/log/debug/plog/*
|
|
export VLLM_ENABLE_GRAPH_MODE=0
|
|
export VLLM_ENABLE_MC2=0
|
|
|
|
torchrun --nproc_per_node ${dp_per_node} --nnodes ${node_size} \
|
|
--node_rank ${node_rank} --master_addr ${master_addr} --master_port ${master_port} \
|
|
data_parallel.py
|