IndexError: list index out of range (Qwen/Qwen2.5-VL-3B-Instruct)

General
1

env: Compute engine
Model: Qwen/Qwen2.5-VL-3B-Instruct
GPU: T4 16GB

command to initialize:

docker run --runtime nvidia --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface -e HUGGING_FACE_HUB_TOKEN=... -p 8000:8000 -e VLLM_USE_V1=0 --ipc=host vllm/vllm-openai:latest --model Qwen/Qwen2.5-VL-3B-Instruct --trust-remote-code --dtype auto --gpu-memory-utilization 0.9 --max-model-len 8192

Why is it that when I just send a text message the response is ok but when I send an image I get this error?

if i sen this one, the return is ok:

{
    "model": "Qwen/Qwen2.5-VL-3B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text", "text": "What is the text in the illustrate?"
                }
            ]
        }
    ]
}

but if i sent image like that, the errors occurs:

{
    "model": "Qwen/Qwen2.5-VL-3B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/qwen.png"
                    }
                },
                {
                    "type": "text", "text": "What is the text in the illustrate?"
                }
            ]
        }
    ]
}

The error:

(APIServer pid=1) ERROR: Exception in ASGI application(APIServer pid=1) Traceback (most recent call last):(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/uvicorn/protocols/http/httptools_impl.py”, line 409, in run_asgi(APIServer pid=1) result = await app( # type: ignore[func-returns-value](APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/uvicorn/middleware/proxy_headers.py”, line 60, in call(APIServer pid=1) return await self.app(scope, receive, send)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/applications.py”, line 1054, in call(APIServer pid=1) await super().call(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/applications.py”, line 113, in call(APIServer pid=1) await self.middleware_stack(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py”, line 186, in call(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py”, line 164, in call(APIServer pid=1) await self.app(scope, receive, _send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py”, line 85, in call(APIServer pid=1) await self.app(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/prometheus_fastapi_instrumentator/middleware.py”, line 177, in call(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/prometheus_fastapi_instrumentator/middleware.py”, line 175, in call(APIServer pid=1) await self.app(scope, receive, send_wrapper)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/exceptions.py”, line 63, in call(APIServer pid=1) await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 53, in wrapped_app(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app(APIServer pid=1) await app(scope, receive, sender)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 716, in call(APIServer pid=1) await self.middleware_stack(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 736, in app(APIServer pid=1) await route.handle(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 290, in handle(APIServer pid=1) await self.app(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 78, in app(APIServer pid=1) await wrap_app_handling_exceptions(app, request)(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 53, in wrapped_app(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app(APIServer pid=1) await app(scope, receive, sender)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 75, in app(APIServer pid=1) response = await f(request)(APIServer pid=1) ^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 302, in app(APIServer pid=1) raw_response = await run_endpoint_function((APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 213, in run_endpoint_function(APIServer pid=1) return await dependant.call(**values)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/utils.py”, line 91, in wrapper(APIServer pid=1) return handler_task.result()(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/utils.py”, line 114, in wrapper(APIServer pid=1) return await func(*args, **kwargs)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 671, in create_chat_completion(APIServer pid=1) generator = await handler.create_chat_completion(request, raw_request)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py”, line 324, in create_chat_completion(APIServer pid=1) return await self.chat_completion_full_generator((APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py”, line 1072, in chat_completion_full_generator(APIServer pid=1) async for res in result_generator:(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/client.py”, line 583, in _process_request(APIServer pid=1) raise request_output(APIServer pid=1) IndexError: list index out of rangeINFO 09-17 15:13:06 [metrics.py:386] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.(APIServer pid=1) WARNING 09-17 15:15:02 [sampling_params.py:311] temperature 1e-06 is less than 0.01, which may cause numerical errors nan or inf in tensors. We have maxed it out to 0.01.(APIServer pid=1) INFO: 177.37.143.134:10075 - “POST /v1/chat/completions HTTP/1.1” 500 Internal Server ErrorINFO 09-17 15:15:02 [metrics.py:386] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 11.7 tokens/s, Running: 0 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%.(APIServer pid=1) ERROR: Exception in ASGI application(APIServer pid=1) Traceback (most recent call last):(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/uvicorn/protocols/http/httptools_impl.py”, line 409, in run_asgi(APIServer pid=1) result = await app( # type: ignore[func-returns-value](APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/uvicorn/middleware/proxy_headers.py”, line 60, in call(APIServer pid=1) return await self.app(scope, receive, send)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/applications.py”, line 1054, in call(APIServer pid=1) await super().call(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/applications.py”, line 113, in call(APIServer pid=1) await self.middleware_stack(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py”, line 186, in call(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/errors.py”, line 164, in call(APIServer pid=1) await self.app(scope, receive, _send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/cors.py”, line 85, in call(APIServer pid=1) await self.app(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/prometheus_fastapi_instrumentator/middleware.py”, line 177, in call(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/prometheus_fastapi_instrumentator/middleware.py”, line 175, in call(APIServer pid=1) await self.app(scope, receive, send_wrapper)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/middleware/exceptions.py”, line 63, in call(APIServer pid=1) await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 53, in wrapped_app(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app(APIServer pid=1) await app(scope, receive, sender)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 716, in call(APIServer pid=1) await self.middleware_stack(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 736, in app(APIServer pid=1) await route.handle(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 290, in handle(APIServer pid=1) await self.app(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 78, in app(APIServer pid=1) await wrap_app_handling_exceptions(app, request)(scope, receive, send)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 53, in wrapped_app(APIServer pid=1) raise exc(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/_exception_handler.py”, line 42, in wrapped_app(APIServer pid=1) await app(scope, receive, sender)(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/starlette/routing.py”, line 75, in app(APIServer pid=1) response = await f(request)(APIServer pid=1) ^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 302, in app(APIServer pid=1) raw_response = await run_endpoint_function((APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/fastapi/routing.py”, line 213, in run_endpoint_function(APIServer pid=1) return await dependant.call(**values)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/utils.py”, line 91, in wrapper(APIServer pid=1) return handler_task.result()(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/utils.py”, line 114, in wrapper(APIServer pid=1) return await func(*args, **kwargs)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py”, line 671, in create_chat_completion(APIServer pid=1) generator = await handler.create_chat_completion(request, raw_request)(APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py”, line 324, in create_chat_completion(APIServer pid=1) return await self.chat_completion_full_generator((APIServer pid=1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/serving_chat.py”, line 1072, in chat_completion_full_generator(APIServer pid=1) async for res in result_generator:(APIServer pid=1) File “/usr/local/lib/python3.12/dist-packages/vllm/engine/multiprocessing/client.py”, line 583, in _process_request(APIServer pid=1) raise request_output(APIServer pid=1) IndexError: list index out of range

2

Your text-only requests work, but image requests to Qwen/Qwen2.5-VL-3B-Instruct return “IndexError: list index out of range” because this is a known bug in vLLM 0.10.x when handling some image inputs, especially with certain image URLs or formats. This error is reproducible and has been reported by other users as well, often when using the OpenAI-compatible API with image content for Qwen2.5-VL models. The issue is not with your request format, which is correct per the OpenAI Vision API spec supported by vLLM.

A workaround is to downgrade to vLLM 0.10.0 (not 0.10.1+) or use a different image URL, as some users report the error disappears with certain images or vLLM versions. If you must use 0.10.1+, you may need to wait for an upstream fix or try serving with VLLM_USE_V1=1 (though this is not always effective). For more, see this issue and this example.

Would you like a step-by-step troubleshooting guide or example code for a working image request?

Sources:

1 Like