chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

update pre-commit config (#18860)

Browse Source
This commit is contained in:
SoluMilken
2026-02-16 00:18:31 +08:00
committed by GitHub
parent f7603203b0
commit 07a24f1a38
135 changed files with 239 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docs/basic_usage/native_api.ipynb
View File

@@ -275,12 +275,10 @@
"metadata": {},
"outputs": [],
"source": [
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"embedding_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-1.5B-instruct \\\n",
" --host 0.0.0.0 --is-embedding --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=embedding_process)"
]
@@ -324,12 +322,10 @@
"metadata": {},
"outputs": [],
"source": [
"reranker_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"reranker_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path BAAI/bge-reranker-v2-m3 \\\n",
" --host 0.0.0.0 --disable-radix-cache --chunked-prefill-size -1 --attention-backend triton --is-embedding --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=reranker_process)"
]
@@ -392,12 +388,10 @@
"metadata": {},
"outputs": [],
"source": [
"score_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"score_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct \\\n",
" --host 0.0.0.0 --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=score_process)"
]
@@ -456,11 +450,9 @@
"# Note that SGLang now treats embedding models and reward models as the same type of models.\n",
"# This will be updated in the future.\n",
"\n",
"reward_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"reward_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path Skywork/Skywork-Reward-Llama-3.1-8B-v0.2 --host 0.0.0.0 --is-embedding --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=reward_process)"
]
@@ -575,11 +567,9 @@
"metadata": {},
"outputs": [],
"source": [
"tokenizer_free_server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"tokenizer_free_server_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=tokenizer_free_server_process)"
]

6
docs/basic_usage/openai_api_embeddings.ipynb
View File

@@ -30,12 +30,10 @@
"from sglang.test.doc_patch import launch_server_cmd\n",
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
"\n",
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"embedding_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-1.5B-instruct \\\n",
" --host 0.0.0.0 --is-embedding --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=embedding_process)"
]

6
docs/basic_usage/openai_api_vision.ipynb
View File

@@ -33,11 +33,9 @@
"from sglang.test.doc_patch import launch_server_cmd\n",
"from sglang.utils import wait_for_server, print_highlight, terminate_process\n",
"\n",
"vision_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"vision_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-7B-Instruct --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=vision_process)"
]

6
docs/basic_usage/send_request.ipynb
View File

@@ -31,12 +31,10 @@
"# This is equivalent to running the following command in your terminal\n",
"# python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct \\\n",
" --host 0.0.0.0 --log-level warning\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]