We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 12a34fa commit 3d0b36aCopy full SHA for 3d0b36a
docs/references/multi_node.md
@@ -9,9 +9,7 @@
9
10
python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 0
11
12
-# replace 172.18.45.52:20000 with your own node ip address and port of the second node
13
-
14
-python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr 172.18.45.52:20000 --nnodes 2 --node-rank 1
+python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 1
15
```
16
17
Note that LLama 405B (fp8) can also be launched on a single node.
0 commit comments