chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[CI] feat: add early exit to wait_for_server when process dies (#18602)

Browse Source
This commit is contained in:
shuwenn
2026-02-13 16:46:09 -08:00
committed by GitHub
parent eccf875d49
commit 3299c4f9c1
33 changed files with 229 additions and 179 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/lora.ipynb
+5 -5
View File
@@ -102,7 +102,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -162,7 +162,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -240,7 +240,7 @@
")\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
"wait_for_server(url)"
"wait_for_server(url, process=server_process)"
]
},
{
@@ -453,7 +453,7 @@
"\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
"wait_for_server(url)"
"wait_for_server(url, process=server_process)"
]
},
{
@@ -610,7 +610,7 @@
")\n",
"\n",
"url = f\"http://127.0.0.1:{port}\"\n",
"wait_for_server(url)"
"wait_for_server(url, process=server_process)"
]
},
{
docs/advanced_features/separate_reasoning.ipynb
+1 -1
View File
@@ -70,7 +70,7 @@
" \"python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-7B --host 0.0.0.0 --reasoning-parser deepseek-r1 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
docs/advanced_features/speculative_decoding.ipynb
+8 -8
View File
@@ -111,7 +111,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -167,7 +167,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -227,7 +227,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -283,7 +283,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -338,7 +338,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -402,7 +402,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -466,7 +466,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -538,7 +538,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
docs/advanced_features/structured_outputs.ipynb
+1 -1
View File
@@ -54,7 +54,7 @@
" \"python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")"
]
},
docs/advanced_features/structured_outputs_for_reasoning_models.ipynb
+1 -1
View File
@@ -50,7 +50,7 @@
" \"python -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-7B --host 0.0.0.0 --reasoning-parser deepseek-r1 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")"
]
},
docs/advanced_features/tool_parser.ipynb
+5 -3
View File
@@ -60,7 +60,7 @@
"server_process, port = launch_server_cmd(\n",
" \"python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-7B-Instruct --tool-call-parser qwen25 --host 0.0.0.0 --log-level warning\" # qwen25\n",
")\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -550,7 +550,9 @@
"server_process_tool_choice, port_tool_choice = launch_server_cmd(\n",
" \"python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-7B-Instruct --tool-call-parser qwen25 --host 0.0.0.0 --log-level warning\"\n",
")\n",
"wait_for_server(f\"http://localhost:{port_tool_choice}\")\n",
"wait_for_server(\n",
" f\"http://localhost:{port_tool_choice}\", process=server_process_tool_choice\n",
")\n",
"\n",
"# Initialize client for tool choice examples\n",
"client_tool_choice = OpenAI(\n",
@@ -695,7 +697,7 @@
"server_process, port = launch_server_cmd(\n",
" \" python3 -m sglang.launch_server --model-path meta-llama/Llama-3.2-1B-Instruct --tool-call-parser pythonic --tp 1 --log-level warning\" # llama-3.2-1b-instruct\n",
")\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"\n",
"tools = [\n",
" {\n",
docs/basic_usage/native_api.ipynb
+7 -7
View File
@@ -49,7 +49,7 @@
" \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
@@ -282,7 +282,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=embedding_process)"
]
},
{
@@ -331,7 +331,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=reranker_process)"
]
},
{
@@ -399,7 +399,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=score_process)"
]
},
{
@@ -462,7 +462,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=reward_process)"
]
},
{
@@ -526,7 +526,7 @@
" \"python3 -m sglang.launch_server --model-path Qwen/Qwen1.5-MoE-A2.7B --host 0.0.0.0 --expert-distribution-recorder-mode stat --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=expert_record_server_process)"
]
},
{
@@ -581,7 +581,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=tokenizer_free_server_process)"
]
},
{
docs/basic_usage/openai_api_completions.ipynb
+1 -1
View File
@@ -39,7 +39,7 @@
" \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"print(f\"Server started on http://localhost:{port}\")"
]
},
docs/basic_usage/openai_api_embeddings.ipynb
+1 -1
View File
@@ -37,7 +37,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=embedding_process)"
]
},
{
docs/basic_usage/openai_api_vision.ipynb
+1 -1
View File
@@ -39,7 +39,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=vision_process)"
]
},
{
docs/basic_usage/send_request.ipynb
+1 -1
View File
@@ -38,7 +38,7 @@
"\"\"\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")"
"wait_for_server(f\"http://localhost:{port}\", process=server_process)"
]
},
{
docs/references/frontend/frontend_tutorial.ipynb
+2 -2
View File
@@ -42,7 +42,7 @@
" \"python -m sglang.launch_server --model-path Qwen/Qwen2.5-7B-Instruct --host 0.0.0.0 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"print(f\"Server started on http://localhost:{port}\")"
]
},
@@ -398,7 +398,7 @@
" \"python -m sglang.launch_server --model-path Qwen/Qwen2.5-VL-7B-Instruct --host 0.0.0.0 --log-level warning\"\n",
")\n",
"\n",
"wait_for_server(f\"http://localhost:{port}\")\n",
"wait_for_server(f\"http://localhost:{port}\", process=server_process)\n",
"print(f\"Server started on http://localhost:{port}\")"
]
},