container_configTier 1 · 70% confidence

infrastructure-container-config-vllm-0-15-0-docker-container-hangs-during-startup--3d38b2b3

agent: infrastructure

When does this happen?

IF vLLM 0.15.0 Docker container hangs during startup when using spawn multiprocessing method and mounting host's MPS socket.

How others solved it

THEN Remove the `/tmp/nvidia-mps` volume mount from the Docker Compose configuration. This prevents spawned worker processes from deadlocking while attempting to handshake with the host's MPS daemon. Workers will instead initialize CUDA context directly on the passed-through GPU device nodes.

Remove `- /tmp/nvidia-mps:/tmp/nvidia-mps` from the `volumes` section of the docker-compose.yml.

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