vllm.config.device ¶
DeviceConfig ¶
Configuration for the device to use for vLLM execution.
Source code in vllm/config/device.py
device class-attribute
instance-attribute
¶
Device type for vLLM execution. This parameter is deprecated and will be removed in a future release. It will now be set automatically based on the current platform.
device_type class-attribute
instance-attribute
¶
Device type from the current platform. This is set in __post_init__
.
__post_init__ ¶
Source code in vllm/config/device.py
compute_hash ¶
compute_hash() -> str
WARNING: Whenever a new field is added to this config, ensure that it is included in the factors list if it affects the computation graph.
Provide a hash that uniquely identifies all the configs that affect the structure of the computation graph from input ids/embeddings to the final hidden states, excluding anything before input ids/embeddings and after the final hidden states.