biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[doc] improve readability for long commands (#19920)

Browse Source 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
Reid
2025-06-23 22:27:07 +08:00
committed by GitHub
parent a6e6604d32
commit 53243e5c42
3 changed files with 48 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/usage/troubleshooting.md
View File

@@ -134,7 +134,10 @@ NCCL_DEBUG=TRACE torchrun --nproc-per-node=<number-of-GPUs> test.py
If you are testing with multi-nodes, adjust `--nproc-per-node` and `--nnodes` according to your setup and set `MASTER_ADDR` to the correct IP address of the master node, reachable from all nodes. Then, run:
```console
NCCL_DEBUG=TRACE torchrun --nnodes 2 --nproc-per-node=2 --rdzv_backend=c10d --rdzv_endpoint=$MASTER_ADDR test.py
NCCL_DEBUG=TRACE torchrun --nnodes 2 \
--nproc-per-node=2 \
--rdzv_backend=c10d \
--rdzv_endpoint=$MASTER_ADDR test.py
```
If the script runs successfully, you should see the message `sanity check is successful!`.