Skip to content

docs: Fix typos and remove incomplete section from vllm multinode doc #3588

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 13, 2025
Merged

docs: Fix typos and remove incomplete section from vllm multinode doc #3588

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 2 additions & 13 deletions docs/backends/vllm/multi-node.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ python -m dynamo.vllm \

Deploy prefill and decode workers on separate nodes for optimized resource utilization:

**Node 1**: Run ingress and prefill workers
**Node 1**: Run ingress and decode worker
```bash
# Start ingress
python -m dynamo.frontend --router-mode kv &
Expand All @@ -85,7 +85,7 @@ python -m dynamo.vllm \
--enforce-eager
```

**Node 2**: Run decode workers
**Node 2**: Run prefill worker
```bash
# Start decode worker
python -m dynamo.vllm \
Expand All @@ -94,14 +94,3 @@ python -m dynamo.vllm \
--enforce-eager \
--is-prefill-worker
```

## Large Model Deployment

For models requiring more GPUs than available on a single node such as tensor-parallel-size 16:

**Node 1**: First part of tensor-parallel model
```bash
# Start ingress
python -m dynamo.frontend --router-mode kv &
```

Loading