chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 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
docs/advanced_features/lora.ipynb
+10 -20
View File
@@ -151,16 +151,14 @@
"metadata": {},
"outputs": [],
"source": [
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
"python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n",
" --lora-paths lora0=algoprog/fact-generation-llama-3.1-8b-instruct-lora \\\n",
" lora1=Nutanix/Meta-Llama-3.1-8B-Instruct_lora_4_alpha_16 \\\n",
" --max-loras-per-batch 2 \\\n",
" --log-level warning \\\n",
"\"\"\"\n",
")\n",
"\"\"\")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
@@ -227,8 +225,7 @@
"\n",
"# The `--target-lora-modules` param below is technically not needed, as the server will infer it from lora0 which already has all the target modules specified.\n",
"# We are adding it here just to demonstrate usage.\n",
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
" python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n",
" --cuda-graph-max-bs 2 \\\n",
@@ -236,8 +233,7 @@
" --max-lora-rank 256\n",
" --lora-target-modules all\n",
" --log-level warning\n",
" \"\"\"\n",
")\n",
" \"\"\")\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
"wait_for_server(url, process=server_process)"
@@ -435,8 +431,7 @@
"metadata": {},
"outputs": [],
"source": [
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
" python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n",
" --cuda-graph-max-bs 8 \\\n",
@@ -448,8 +443,7 @@
" {\"lora_name\":\"lora1\",\"lora_path\":\"algoprog/fact-generation-llama-3.1-8b-instruct-lora\"} \\\n",
" lora2=philschmid/code-llama-3-1-8b-text-to-sql-lora\n",
" --log-level warning\n",
" \"\"\"\n",
")\n",
" \"\"\")\n",
"\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
@@ -548,16 +542,14 @@
"metadata": {},
"outputs": [],
"source": [
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
" python3 -m sglang.launch_server \\\n",
" --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n",
" --lora-backend csgmv \\\n",
" --max-loras-per-batch 16 \\\n",
" --lora-paths lora1=path/to/lora1 lora2=path/to/lora2\n",
" \"\"\"\n",
")"
" \"\"\")"
]
},
{
@@ -594,8 +586,7 @@
"lora2 = \"philschmid/code-llama-3-1-8b-text-to-sql-lora\"\n",
"\n",
"\n",
"server_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"server_process, port = launch_server_cmd(\"\"\"\n",
" python3 -m sglang.launch_server \\\n",
" --model-path meta-llama/Meta-Llama-3.1-8B-Instruct \\\n",
" --enable-lora \\\n",
@@ -606,8 +597,7 @@
" --max-lora-rank 256 \\\n",
" --max-loras-per-batch 2 \\\n",
" --max-loaded-loras 4\n",
" \"\"\"\n",
")\n",
" \"\"\")\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
"wait_for_server(url, process=server_process)"
docs/advanced_features/structured_outputs.ipynb
-1
View File
@@ -740,7 +740,6 @@
"import json\n",
"from pydantic import BaseModel, Field\n",
"\n",
"\n",
"prompts = [\n",
" \"Give me the information of the capital of China in the JSON format.\",\n",
" \"Give me the information of the capital of France in the JSON format.\",\n",
docs/advanced_features/structured_outputs_for_reasoning_models.ipynb
-1
View File
@@ -642,7 +642,6 @@
"import json\n",
"from pydantic import BaseModel, Field\n",
"\n",
"\n",
"prompts = [\n",
" \"Give me the information of the capital of China in the JSON format.\",\n",
" \"Give me the information of the capital of France in the JSON format.\",\n",
docs/advanced_features/vlm_query.ipynb
-1
View File
@@ -117,7 +117,6 @@
"source": [
"from sglang import Engine\n",
"\n",
"\n",
"llm = Engine(model_path=model_path, chat_template=chat_template, log_level=\"warning\")"
]
},
docs/basic_usage/native_api.ipynb
+10 -20
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)"
]
docs/basic_usage/openai_api_embeddings.ipynb
+2 -4
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)"
]
docs/basic_usage/openai_api_vision.ipynb
+2 -4
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)"
]
docs/basic_usage/send_request.ipynb
+2 -4
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)"
]