vllm.model_executor.layers.mamba.kda_checkpoint
¶
Classes:
-
FlashKDAPrefillCheckpointExporter–Store KDA (FlashKDA or Triton) recurrent and convolution checkpoint states.
FlashKDAPrefillCheckpointExporter
dataclass
¶
Bases: MambaPrefillCheckpointExporter
Store KDA (FlashKDA or Triton) recurrent and convolution checkpoint states.