# vLLM v0.15.1 failing when deployed in AWS **URL:** \ **Category:** General\ **Created:** [February 5, 2026, 9:01pm UTC](https://discuss.vllm.ai/t/vllm-v0-15-1-failing-when-deployed-in-aws/2335 "2026-02-05T21:01:17Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![birchsport](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/birchsport/32/1128_2.png) [@birchsport](https://discuss.vllm.ai/u/birchsport)\ **Post date:** [February 5, 2026, 9:01pm UTC](https://discuss.vllm.ai/t/vllm-v0-15-1-failing-when-deployed-in-aws/2335/1 "2026-02-05T21:01:17Z")
Not sure which category to use for this question. We have been running vllm up to v0.14.1 on a p5en.48xlarge in AWS on our EKS cluster, serving gpt-oss-120b. However, when we tried to push v0.15.0 and v0.15.1, we were unsuccessful. I found two open issues ([[Bug]: Issue with vllm 0.15.0 image - running via docker · Issue #33447 · vllm-project/vllm · GitHub](https://github.com/vllm-project/vllm/issues/33447) and [[Bug]: Serving model in 0.15.0 Docker container hangs - 0.14.1 worked fine · Issue #33369 · vllm-project/vllm · GitHub](https://github.com/vllm-project/vllm/issues/33369)) similar to what we are seeing, but the workaround in the second one did not help. We have upgraded our instance AMI to the latest as of this morning, hoping it might be a driver issue, but that did not resolve things. Here is a snippet of the error we see on startup. ```auto ERROR 01-30 12:09:33 [multiproc_executor.py:772] WorkerProc failed to start. ERROR 01-30 12:09:33 [multiproc_executor.py:772] Traceback (most recent call last): ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 743, in worker_main ERROR 01-30 12:09:33 [multiproc_executor.py:772] worker = WorkerProc(*args, **kwargs) ERROR 01-30 12:09:33 [multiproc_executor.py:772] ^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 569, in __init__ ERROR 01-30 12:09:33 [multiproc_executor.py:772] self.worker.init_device() ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 326, in init_device ERROR 01-30 12:09:33 [multiproc_executor.py:772] self.worker.init_device() # type: ignore ERROR 01-30 12:09:33 [multiproc_executor.py:772] ^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 210, in init_device ERROR 01-30 12:09:33 [multiproc_executor.py:772] current_platform.set_device(self.device) ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/vllm/platforms/cuda.py", line 123, in set_device ERROR 01-30 12:09:33 [multiproc_executor.py:772] torch.cuda.set_device(device) ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/torch/cuda/ __init__.py", line 567, in set_device ERROR 01-30 12:09:33 [multiproc_executor.py:772] torch._C._cuda_setDevice(device) ERROR 01-30 12:09:33 [multiproc_executor.py:772] File "/usr/local/lib/python3.12/dist-packages/torch/cuda/ __init__.py", line 410, in _lazy_init ERROR 01-30 12:09:33 [multiproc_executor.py:772] torch._C._cuda_init() ERROR 01-30 12:09:33 [multiproc_executor.py:772] RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination ``` Would anyone be able to provide us with some direction on how we might resolve this issue? Our Docker image is using this base: `vllm/vllm-openai:v0.15.1` Thank you! ---
**Author:** ![RunLLM](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/runllm/32/233_2.png) [@RunLLM](https://discuss.vllm.ai/u/RunLLM)\ **Post date:** [February 5, 2026, 9:01pm UTC](https://discuss.vllm.ai/t/vllm-v0-15-1-failing-when-deployed-in-aws/2335/2 "2026-02-05T21:01:53Z")
Your error (`Error 803: system has unsupported display driver / cuda driver combination`) is a known issue with vLLM v0.15.x Docker images on newer NVIDIA drivers (e.g., Blackwell GPUs, CUDA 13.x). The root cause is a conflict between the container’s CUDA compatibility libraries and the host’s driver, which leads to the wrong `libcuda.so` being loaded. The workaround in [issue #33369](https://github.com/vllm-project/vllm/issues/33369) and [issue #33447](https://github.com/vllm-project/vllm/issues/33447) is to remove or override the `/etc/ld.so.conf.d/00-cuda-compat.conf` file in the container, but this does not always work with the latest images or drivers. A more robust solution is to explicitly set the `LD_LIBRARY_PATH` in your Docker container to prioritize the host’s NVIDIA driver libraries and exclude the container’s CUDA toolkit paths. For example, set: ```yaml LD_LIBRARY_PATH: '/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/lib/x86_64-linux-gnu' ``` in your container environment, and ensure you do **not** mount `/tmp/nvidia-mps` if using multiprocessing with `spawn` (the new default in v0.15.x). This approach has been confirmed to resolve the error on Blackwell/590+ drivers and CUDA 13.x ([see details](https://github.com/vllm-project/vllm/issues/33369)). If this does not resolve your issue, you may need to wait for a backported fix in a future vLLM release. Would you like a step-by-step breakdown or a sample Docker Compose snippet? Sources: - [vllm issue #33369](https://github.com/vllm-project/vllm/issues/33369) - [vllm issue #33447](https://github.com/vllm-project/vllm/issues/33447) Hint: Mention @RunLLM in the post for followups. ---
**Author:** ![birchsport](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/birchsport/32/1128_2.png) [@birchsport](https://discuss.vllm.ai/u/birchsport)\ **Post date:** [February 5, 2026, 11:47pm UTC](https://discuss.vllm.ai/t/vllm-v0-15-1-failing-when-deployed-in-aws/2335/3 "2026-02-05T23:47:28Z")
I have tried many combinations of LD\_LIBRARY\_PATH overrides and have not found a working path yet. Some more details: ```auto AWS Instance Type: p5en.48xlarge AMI Type: BOTTLEROCKET_x86_64_NVIDIA AMI Version: 1.54.0-5043decc ``` ---
**Author:** ![birchsport](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.vllm.ai/birchsport/32/1128_2.png) [@birchsport](https://discuss.vllm.ai/u/birchsport)\ **Post date:** [February 6, 2026, 3:40pm UTC](https://discuss.vllm.ai/t/vllm-v0-15-1-failing-when-deployed-in-aws/2335/4 "2026-02-06T15:40:13Z")
Follow-up: the nightly build works fine (version 0.15.2rc1.dev), so this appears to be addressed. Will use this til the next release.