Skip to content

Commit df54b9c

Browse files
docs: update close-deployment in dynamo_serve.md (ai-dynamo#535)
Co-authored-by: ishandhanani <[email protected]>
1 parent c1c875b commit df54b9c

File tree

3 files changed

+7
-21
lines changed

3 files changed

+7
-21
lines changed

docs/guides/dynamo_serve.md

Lines changed: 5 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -235,20 +235,10 @@ curl localhost:8000/v1/chat/completions -H "Content-Type: application/json"
235235
}'
236236
```
237237

238-
## Close your deployment
238+
## Close deployment
239239

240-
If you have any lingering processes after running `ctrl-c`, you can kill them by running
240+
> [!IMPORTANT]
241+
> We are aware of an issue where vLLM subprocesses might not be killed when `ctrl-c` is pressed.
242+
> We are working on addressing this. Relevant vLLM issues can be found [here](https://github.com/vllm-project/vllm/pull/8492) and [here](https://github.com/vllm-project/vllm/issues/6219#issuecomment-2439257824).
241243
242-
```bash
243-
function kill_tree() {
244-
local parent=$1
245-
local children=$(ps -o pid= --ppid $parent)
246-
for child in $children; do
247-
kill_tree $child
248-
done
249-
echo "Killing process $parent"
250-
kill -9 $parent
251-
}
252-
253-
kill_tree $(pgrep circusd)
254-
```
244+
To stop the serve, you can press `ctrl-c` which will kill the different components. In order to kill the remaining vLLM subprocesses you can run `nvidia-smi` and `kill -9` the remaining processes or run `pkill python3` from inside of the container.

examples/llm/README.md

Lines changed: 1 addition & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -157,8 +157,4 @@ See [multinode-examples.md](multinode-examples.md) for more details.
157157

158158
### Close deployment
159159

160-
> [!IMPORTANT]
161-
> We are aware of an issue where vLLM subprocesses might not be killed when `ctrl-c` is pressed.
162-
> We are working on addressing this. Relevant vLLM issues can be found [here](https://github.com/vllm-project/vllm/pull/8492) and [here](https://github.com/vllm-project/vllm/issues/6219#issuecomment-2439257824).
163-
164-
To stop the serve, you can press `ctrl-c` which will kill the different components. In order to kill the remaining vLLM subprocesses you can run `nvidia-smi` and `kill -9` the remaining processes or run `pkill python3` from inside of the container.
160+
See [close deployment](../../docs/guides/dynamo_serve.md#close-deployment) section to learn about how to close the deployment.

examples/tensorrt_llm/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -119,7 +119,7 @@ See [client](../llm/README.md#client) section to learn how to send request to th
119119

120120
### Close deployment
121121

122-
See [close deployment](../llm/README.md#close-deployment) section to learn about how to close the deployment.
122+
See [close deployment](../../docs/guides/dynamo_serve.md#close-deployment) section to learn about how to close the deployment.
123123

124124
Remaining tasks:
125125

0 commit comments

Comments
 (0)