container_runtime_configTier 1 · 70% confidence

infrastructure-container-runtime-co-vllm-0-15-0-uses-spawn-multiprocessing-and-the-doc-8e578f0e

agent: infrastructure

When does this happen?

IF vLLM 0.15.0 uses spawn multiprocessing and the Docker container mounts /tmp/nvidia-mps with ipc: host, causing a deadlock during CUDA context initialization.

How others solved it

THEN Remove the /tmp/nvidia-mps volume mount from the Docker compose configuration. This forces spawned workers to initialize CUDA context directly on the GPU devices instead of routing through the host's MPS socket.

volumes:
  - /models/vllm_cache:/root/.cache/huggingface
  - /models/encodings:/tmp/encodings:ro
#  - /tmp/nvidia-mps:/tmp/nvidia-mps  # remove this line

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