Skip to content

Commit 7f7af2a

Browse files
committed
update app create
1 parent 73d74ca commit 7f7af2a

File tree

1 file changed

+5
-5
lines changed

1 file changed

+5
-5
lines changed

articles/container-apps/serverless-gpu-nim.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -166,12 +166,12 @@ Next you create a container app with the NVIDIA GPU Cloud API key.
166166
--image $ACR_NAME.azurecr.io/$CONTAINER_AND_TAG \
167167
--cpu 24 \
168168
--memory 220 \
169-
--gpu "NVIDIAA100" \
169+
--target-port 8000 \
170+
--ingress external \
170171
--secrets ngc-api-key=<PASTE_NGC_API_KEY_HERE> \
171172
--env-vars NGC_API_KEY=secretref:ngc-api-key \
172173
--registry-server $ACR_NAME.azurecr.io \
173-
--registry-username <ACR_USERNAME> \
174-
--registry-password <ACR_PASSWORD> \
174+
--workload-profile-name LLAMA_PROFILE \
175175
--query properties.configuration.ingress.fqdn
176176
```
177177
@@ -189,8 +189,8 @@ curl -X POST \
189189
-H 'accept: application/json' \
190190
-H 'Content-Type: application/json' \
191191
-d '{
192-
"model": "meta/llama3-8b-instruct",
193-
"prompt": "Once upon a time",
192+
"model": "meta/llama-3.1-8b-instruct",
193+
"prompt": [{"role":"user", "content":"Once upon a time..."}],
194194
"max_tokens": 64
195195
}'
196196
```

0 commit comments

Comments
 (0)