add

20251011.md

@@ -0,0 +1,147 @@
+## 崩溃原因
+
+- 一个请求被发送到 vLLM 服务，该请求包含了结构化输出的意图
+- vLLM 在处理请求时，进入 structured_output_request.structured_output_key 的逻辑，最终调用 get_structured_output_key(sampling_params)函数。
+- 该函数遍历 sampling_params 中的各种参数（如 grammar, json_schema, regex 等），但没有找到任何一个有效的结构化输出参数。
+- 因此抛出异常：raise ValueError("No valid structured output parameter found")
+- 这个 ValueError 在后台线程中抛出，但未被捕获，导致 EngineCore 进程（PID 2738693）崩溃
+- 主 API 服务（APIServer）检测到 EngineCore 崩溃，抛出 EngineDeadError，最终整个服务终止。
+
+## 解决方案一
+
+确保请求进入vllm的时候，提供有效的结构化输出参数。例如：
+
+```json
+{
+  "prompt": "生成一个用户信息",
+  "structured_output": {
+    "type": "json",
+    "schema": {
+      "type": "object",
+      "properties": {
+        "name": {"type": "string"},
+        "age": {"type": "integer"}
+      },
+      "required": ["name", "age"]
+    }
+  }
+}
+```
+
+##### 错误示例
+
+```json
+{
+  "prompt": "生成一个JSON",
+  "structured_output": {}
+}
+```
+
+```json
+{
+  "prompt": "生成一个JSON",
+  "json_schema": null
+}
+```
+
+## 解决方案二
+
+升级vllm的版本到最新稳定版，官方已做出大量优化和改进。
+
+## 崩溃日志片段
+
+```text
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710] EngineCore encountered a fatal error.
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710] Traceback (most recent call last):
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 701, in run_engine_core
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     engine_core.run_busy_loop()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 728, in run_busy_loop
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     self._process_engine_step()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 754, in _process_engine_step
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     outputs, model_executed = self.step_fn()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 283, in step
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     scheduler_output = self.scheduler.schedule()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/core/sched/scheduler.py", line 359, in schedule
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     if structured_output_req and structured_output_req.grammar:
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 45, in grammar
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     completed = self._check_grammar_completion()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 33, in _check_grammar_completion
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     self._grammar = self._grammar.result(timeout=0.0001)
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/_base.py", line 458, in result
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     return self.__get_result()
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     raise self._exception
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/thread.py", line 58, in run
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     result = self.fn(*self.args, **self.kwargs)
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/__init__.py", line 128, in _async_create_grammar
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     key = request.structured_output_request.structured_output_key  # type: ignore[union-attr]
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/functools.py", line 981, in __get__
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     val = self.func(instance)
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 58, in structured_output_key
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     return get_structured_output_key(self.sampling_params)
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 86, in get_structured_output_key
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710]     raise ValueError("No valid structured output parameter found")
+(EngineCore_DP0 pid=2738693) ERROR 10-10 10:43:10 [core.py:710] ValueError: No valid structured output parameter found
+(EngineCore_DP0 pid=2738693) Process EngineCore_DP0:
+(EngineCore_DP0 pid=2738693) Traceback (most recent call last):
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480] AsyncLLM output_handler failed.
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480] Traceback (most recent call last):
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/async_llm.py", line 439, in output_handler
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480]     outputs = await engine_core.get_output_async()
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core_client.py", line 846, in get_output_async
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480]     raise self._format_exception(outputs) from None
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [async_llm.py:480] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
+(EngineCore_DP0 pid=2738693)     self.run()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/multiprocessing/process.py", line 108, in run
+(EngineCore_DP0 pid=2738693)     self._target(*self._args, **self._kwargs)
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 712, in run_engine_core
+(EngineCore_DP0 pid=2738693)     raise e
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 701, in run_engine_core
+(EngineCore_DP0 pid=2738693)     engine_core.run_busy_loop()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 728, in run_busy_loop
+(EngineCore_DP0 pid=2738693)     self._process_engine_step()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 754, in _process_engine_step
+(EngineCore_DP0 pid=2738693)     outputs, model_executed = self.step_fn()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core.py", line 283, in step
+(EngineCore_DP0 pid=2738693)     scheduler_output = self.scheduler.schedule()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/core/sched/scheduler.py", line 359, in schedule
+(EngineCore_DP0 pid=2738693)     if structured_output_req and structured_output_req.grammar:
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 45, in grammar
+(EngineCore_DP0 pid=2738693)     completed = self._check_grammar_completion()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 33, in _check_grammar_completion
+(EngineCore_DP0 pid=2738693)     self._grammar = self._grammar.result(timeout=0.0001)
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/_base.py", line 458, in result
+(EngineCore_DP0 pid=2738693)     return self.__get_result()
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
+(EngineCore_DP0 pid=2738693)     raise self._exception
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/concurrent/futures/thread.py", line 58, in run
+(EngineCore_DP0 pid=2738693)     result = self.fn(*self.args, **self.kwargs)
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/__init__.py", line 128, in _async_create_grammar
+(EngineCore_DP0 pid=2738693)     key = request.structured_output_request.structured_output_key  # type: ignore[union-attr]
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/functools.py", line 981, in __get__
+(EngineCore_DP0 pid=2738693)     val = self.func(instance)
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 58, in structured_output_key
+(EngineCore_DP0 pid=2738693)     return get_structured_output_key(self.sampling_params)
+(EngineCore_DP0 pid=2738693)   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/structured_output/request.py", line 86, in get_structured_output_key
+(EngineCore_DP0 pid=2738693)     raise ValueError("No valid structured output parameter found")
+(EngineCore_DP0 pid=2738693) ValueError: No valid structured output parameter found
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145] Error in chat completion stream generator.
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145] Traceback (most recent call last):
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/entrypoints/openai/serving_chat.py", line 574, in chat_completion_stream_generator
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]     async for res in result_generator:
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/async_llm.py", line 387, in generate
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]     out = q.get_nowait() or await q.get()
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/output_processor.py", line 59, in get
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]     raise output
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/async_llm.py", line 439, in output_handler
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]     outputs = await engine_core.get_output_async()
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]   File "/aisoft/conda/env/vllm2/lib/python3.10/site-packages/vllm/v1/engine/core_client.py", line 846, in get_output_async
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145]     raise self._format_exception(outputs) from None
+(APIServer pid=2738423) ERROR 10-10 10:43:10 [serving_chat.py:1145] vllm.v1.engine.exceptions.EngineDeadError: EngineCore encountered an issue. See stack trace (above) for the root cause.
+[rank0]:[W1010 10:43:10.666166970 ProcessGroupNCCL.cpp:1538] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
+(APIServer pid=2738423) INFO:     Shutting down
+(APIServer pid=2738423) INFO:     Waiting for application shutdown.
+(APIServer pid=2738423) INFO:     Application shutdown complete.
+(APIServer pid=2738423) INFO:     Finished server process [2738423]
+```