EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[CI] Improve Docs CI Efficiency (#3587)

Browse Source 
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
This commit is contained in:
Shi Shuai
2025-02-15 03:57:00 +00:00
committed by GitHub
parent 862dd76c76
commit 7443197a63
19 changed files with 366 additions and 231 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
docs/backend/structured_outputs.ipynb
View File

@@ -38,24 +38,26 @@
"metadata": {},
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
" wait_for_server,\n",
" terminate_process,\n",
" print_highlight,\n",
")\n",
"import openai\n",
"import os\n",
"from sglang.test.test_utils import is_in_ci\n",
"\n",
"if is_in_ci():\n",
" from patch import launch_server_cmd\n",
"else:\n",
" from sglang.utils import launch_server_cmd\n",
"\n",
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
"\n",
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
"\n",
"\n",
"server_process = execute_shell_command(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --port 30000 --host 0.0.0.0 --grammar-backend xgrammar\"\n",
"server_process, port = launch_server_cmd(\n",
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0 --grammar-backend xgrammar\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30000\")\n",
"client = openai.Client(base_url=\"http://127.0.0.1:30000/v1\", api_key=\"None\")"
"wait_for_server(f\"http://localhost:{port}\")\n",
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")"
]
},
{
@@ -264,7 +266,7 @@
"\n",
"# Make API request\n",
"response = requests.post(\n",
" \"http://localhost:30000/generate\",\n",
" f\"http://localhost:{port}/generate\",\n",
" json={\n",
" \"text\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
" \"sampling_params\": {\n",
@@ -309,7 +311,7 @@
"\n",
"# JSON\n",
"response = requests.post(\n",
" \"http://localhost:30000/generate\",\n",
" f\"http://localhost:{port}/generate\",\n",
" json={\n",
" \"text\": \"Here is the information of the capital of France in the JSON format.\\n\",\n",
" \"sampling_params\": {\n",
@@ -339,7 +341,7 @@
"import requests\n",
"\n",
"response = requests.post(\n",
" \"http://localhost:30000/generate\",\n",
" f\"http://localhost:{port}/generate\",\n",
" json={\n",
" \"text\": \"Give me the information of the capital of France.\",\n",
" \"sampling_params\": {\n",
@@ -376,7 +378,7 @@
"outputs": [],
"source": [
"response = requests.post(\n",
" \"http://localhost:30000/generate\",\n",
" f\"http://localhost:{port}/generate\",\n",
" json={\n",
" \"text\": \"Paris is the capital of\",\n",
" \"sampling_params\": {\n",
@@ -395,7 +397,7 @@
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)"
"terminate_process(server_process, port)"
]
},
{