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

42
docs/backend/openai_api_completions.ipynb
View File

@@ -33,18 +33,22 @@
"metadata": {},
"outputs": [],
"source": [
"from sglang.utils import (\n",
" execute_shell_command,\n",
" wait_for_server,\n",
" terminate_process,\n",
" print_highlight,\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",
"\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\"\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 30020 --host 0.0.0.0\"\n",
")\n",
"\n",
"wait_for_server(\"http://localhost:30020\")"
"wait_for_server(f\"http://localhost:{port}\")\n",
"print(f\"Server started on http://localhost:{port}\")"
]
},
{
@@ -68,7 +72,7 @@
"source": [
"import openai\n",
"\n",
"client = openai.Client(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
@@ -245,7 +249,7 @@
"import time\n",
"from openai import OpenAI\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"requests = [\n",
" {\n",
@@ -348,10 +352,10 @@
"import time\n",
"from openai import OpenAI\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"requests = []\n",
"for i in range(100):\n",
"for i in range(20):\n",
" requests.append(\n",
" {\n",
" \"custom_id\": f\"request-{i}\",\n",
@@ -369,7 +373,7 @@
" \"content\": \"Write a detailed story about topic. Make it very long.\",\n",
" },\n",
" ],\n",
" \"max_tokens\": 500,\n",
" \"max_tokens\": 64,\n",
" },\n",
" }\n",
" )\n",
@@ -425,10 +429,10 @@
"from openai import OpenAI\n",
"import os\n",
"\n",
"client = OpenAI(base_url=\"http://127.0.0.1:30020/v1\", api_key=\"None\")\n",
"client = OpenAI(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
"\n",
"requests = []\n",
"for i in range(500):\n",
"for i in range(5000):\n",
" requests.append(\n",
" {\n",
" \"custom_id\": f\"request-{i}\",\n",
@@ -446,7 +450,7 @@
" \"content\": \"Write a detailed story about topic. Make it very long.\",\n",
" },\n",
" ],\n",
" \"max_tokens\": 500,\n",
" \"max_tokens\": 128,\n",
" },\n",
" }\n",
" )\n",
@@ -508,7 +512,7 @@
"metadata": {},
"outputs": [],
"source": [
"terminate_process(server_process)"
"terminate_process(server_process, port)"
]
}
],