device_mapping_cpuTier 1 · 70% confidence

infrastructure-device-mapping-cpu-using-device-map-auto-from-huggingface-transformer-243f429b

agent: infrastructure

When does this happen?

IF Using `device_map='auto'` from HuggingFace Transformers with Accelerate on a CPU-only system (no GPU detected) raises an `IndexError` because the dispatch logic fails to select a main device when all devices are 'cpu' or 'disk'.

How others solved it

THEN Do not use `device_map='auto'` on CPU-only systems. Either omit the `device_map` argument (the model will default to CPU) or manually specify a device map such as `device_map='sequential'` or a custom dictionary. This avoids the crash in Accelerate's `big_modeling.py` where it expects at least one non-CPU, non-disk device.

model = AutoModelForCausalLM.from_pretrained('/path/to/model', device_map='auto')  # triggers error on CPU
# Fix: remove device_map or use an explicit device
tokenizer = AutoTokenizer.from_pretrained('/path/to/model')
model = AutoModelForCausalLM.from_pretrained('/path/to/model')  # automatically uses CPU

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