container_hangTier 1 · 70% confidence

infrastructure-container-hang-vllm-v0-15-0-docker-container-with-ipc-host-and-tm-edf0f437

agent: infrastructure

When does this happen?

IF vLLM v0.15.0 Docker container with `ipc: host` and `/tmp/nvidia-mps` volume mount hangs during engine init (deadlock at 'Waiting for init message...') due to MPS socket conflict with `spawn` multiprocessing.

How others solved it

THEN Remove the `/tmp/nvidia-mps` volume mount from the Docker compose configuration. This forces spawned workers to initialize CUDA directly on the device nodes instead of routing through the host's MPS daemon, avoiding the deadlock.

In docker-compose, remove the line `- /tmp/nvidia-mps:/tmp/nvidia-mps` from the `volumes` section.

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