Skip to content

vllm.model_executor.layers.mamba.kda_checkpoint

Classes:

FlashKDAPrefillCheckpointExporter dataclass

Bases: MambaPrefillCheckpointExporter

Store KDA (FlashKDA or Triton) recurrent and convolution checkpoint states.

Source code in vllm/model_executor/layers/mamba/kda_checkpoint.py
class FlashKDAPrefillCheckpointExporter(MambaPrefillCheckpointExporter):
    """Store KDA (FlashKDA or Triton) recurrent and convolution checkpoint states."""