MCPcopy Create free account
hub / github.com/abetlen/llama-cpp-python / attention_partitioned

Method attention_partitioned

examples/server/server.py:11760–11761  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

11758
11759 @property
11760 def attention_partitioned(self) -> bool:
11761 return self.memory_model == "attention-partitioned"
11762
11763 @property
11764 def request_context_limit(self) -> int:

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected