[NPU] Docs op performance optimize (#28277)
This commit is contained in:
@@ -16,7 +16,7 @@ This notebook provides a quick-start guide to use SGLang in chat completions aft
|
||||
|
||||
```python Example
|
||||
from sglang.test.doc_patch import launch_server_cmd
|
||||
from sglang.utils import wait_for_server, print_highlight, terminate_process
|
||||
from sglang.utils import wait_for_server, terminate_process
|
||||
|
||||
# This is equivalent to running the following command in your terminal
|
||||
# python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0
|
||||
@@ -46,7 +46,7 @@ curl -s http://localhost:{port}/v1/chat/completions \
|
||||
"""
|
||||
|
||||
response = json.loads(subprocess.check_output(curl_command, shell=True))
|
||||
print_highlight(response)
|
||||
print(response)
|
||||
```
|
||||
|
||||
## Using Python Requests
|
||||
@@ -64,7 +64,7 @@ data = {
|
||||
}
|
||||
|
||||
response = requests.post(url, json=data)
|
||||
print_highlight(response.json())
|
||||
print(response.json())
|
||||
```
|
||||
|
||||
## Using OpenAI Python Client
|
||||
@@ -84,7 +84,7 @@ response = client.chat.completions.create(
|
||||
temperature=0,
|
||||
max_tokens=64,
|
||||
)
|
||||
print_highlight(response)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### Streaming
|
||||
@@ -133,7 +133,7 @@ response = requests.post(
|
||||
},
|
||||
)
|
||||
|
||||
print_highlight(response.json())
|
||||
print(response.json())
|
||||
```
|
||||
### Streaming
|
||||
|
||||
|
||||
Reference in New Issue
Block a user