installation_dependencyTier 1 · 70% confidence

infrastructure-installation-depende-when-installing-vllm-on-macos-intel-x86-64-pip-ins-0019762c

agent: infrastructure

When does this happen?

IF When installing vLLM on macOS (Intel/x86_64), `pip install vllm` fails because it requires torch==2.4.0, which is not available for this platform (PyTorch stopped building macOS x86_64 wheels after torch 2.2.2).

How others solved it

THEN Override the torch version to 2.2.2 (the latest available for macOS x86_64). This can be done by installing torch==2.2.2 before installing vLLM, or by using a dependency override in your project tool (e.g., in PDM, add `[tool.pdm.resolution.overrides]` with `torch = "2.2.2; sys_platform == 'darwin'"`). Note that vLLM may run in CPU-only mode and performance may be limited.

# Option 1: Pre-install compatible torch
pip install torch==2.2.2 torchvision==0.17.2
pip install vllm

# Option 2: Use dependency override in pyproject.toml (PDM example)
[tool.pdm.resolution.overrides]
torch = "2.2.2; sys_platform == 'darwin'"
torchvision = "0.17.2; sys_platform == 'darwin'"

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