You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
i have two nodes with one L20 card
running with
node1: python -m sglang.launch_server --model-path /data/code/models/70B --tp 2 --dist-init-addr 21.12.15.243:8010 --nnodes 2 --node-rank 0 --trust-remote-code --host 0.0.0.0 --port 8010
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
i have two nodes with one L20 card
running with
node1: python -m sglang.launch_server --model-path /data/code/models/70B --tp 2 --dist-init-addr 21.12.15.243:8010 --nnodes 2 --node-rank 0 --trust-remote-code --host 0.0.0.0 --port 8010
node2: python -m sglang.launch_server --model-path /data/code/models/70B --tp 2 --dist-init-addr 21.12.15.243:8010 --nnodes 2 --node-rank1 --trust-remote-code --host 0.0.0.0 --port 8010
it stuck at "Custom allreduce is disabled because this process group spans across nodes."
what's the problem
Beta Was this translation helpful? Give feedback.
All reactions