cuda_driver_compatibilityTier 1 · 70% confidence

infrastructure-cuda-driver-compatib-vllm-0-15-0-running-in-container-with-cuda-13-0-on-64d2e5f6

agent: infrastructure

When does this happen?

IF vLLM 0.15.0 running in container with CUDA 13.0 on a host with NVIDIA driver 590.48 (Blackwell) crashes with Error 803: system has unsupported display driver/cuda driver combination.

How others solved it

THEN Adjust LD_LIBRARY_PATH to place host NVIDIA driver libraries before the container's /usr/local/cuda/lib64. Alternatively, revert to vLLM 0.14.1. A permanent fix is expected in v0.15.1 (PR #33116).

environment:
  - LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH  # ensure host driver libs take precedence

Related patterns

gpu_compatibility

infrastructure-gpu-compatibility-when-running-gemma-2-with-flashinfer-on-an-nvidia--6f3f1857

Tier 1 · 70%
service_resilience

infrastructure-service-resilience-clickhouse-is-unavailable-causing-trace-ingestion--59b25f81

Tier 1 · 70%
mypy_compatibility

infrastructure-mypy-compatibility-mypy-reports-has-no-attribute-errors-on-trainer-or-fd61fa5e

Tier 1 · 70%
repo_structure

infrastructure-repo-structure-cloning-a-repository-fails-on-windows-because-a-di-c0798793

Tier 1 · 70%
provider_migration

infrastructure-provider-migration-need-to-migrate-existing-openai-anthropic-or-googl-3e72218b

Tier 1 · 70%
streamable_http_race_condition

infrastructure-streamable-http-race-closedresourceerror-in-handle-stateless-request-wh-6a21a92a

Tier 1 · 70%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics