Skip to content

Commit 3efd1d1

Browse files
authored
fixed try it out section in quickstart (#1197)
Signed-off-by: Nir Rozenbaum <[email protected]>
1 parent 1c51047 commit 3efd1d1

File tree

1 file changed

+11
-27
lines changed

1 file changed

+11
-27
lines changed

site-src/guides/index.md

Lines changed: 11 additions & 27 deletions
Original file line numberDiff line numberDiff line change
@@ -248,33 +248,17 @@ This quickstart guide is intended for engineers familiar with k8s and model serv
248248

249249
Wait until the gateway is ready.
250250

251-
=== "GPU-Based Model Server"
252-
253-
```bash
254-
IP=$(kubectl get gateway/inference-gateway -o jsonpath='{.status.addresses[0].value}')
255-
PORT=80
256-
257-
curl -i ${IP}:${PORT}/v1/completions -H 'Content-Type: application/json' -d '{
258-
"model": "food-review",
259-
"prompt": "Write as if you were a critic: San Francisco",
260-
"max_tokens": 100,
261-
"temperature": 0
262-
}'
263-
```
264-
265-
=== "CPU-Based Model Server"
266-
267-
```bash
268-
IP=$(kubectl get gateway/inference-gateway -o jsonpath='{.status.addresses[0].value}')
269-
PORT=80
270-
271-
curl -i ${IP}:${PORT}/v1/completions -H 'Content-Type: application/json' -d '{
272-
"model": "Qwen/Qwen2.5-1.5B-Instruct",
273-
"prompt": "Write as if you were a critic: San Francisco",
274-
"max_tokens": 100,
275-
"temperature": 0
276-
}'
277-
```
251+
```bash
252+
IP=$(kubectl get gateway/inference-gateway -o jsonpath='{.status.addresses[0].value}')
253+
PORT=80
254+
255+
curl -i ${IP}:${PORT}/v1/completions -H 'Content-Type: application/json' -d '{
256+
"model": "food-review",
257+
"prompt": "Write as if you were a critic: San Francisco",
258+
"max_tokens": 100,
259+
"temperature": 0
260+
}'
261+
```
278262

279263
### Cleanup
280264

0 commit comments

Comments
 (0)