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

Method __init__

llama_cpp/llama_cache.py:52–57  ·  view source on GitHub ↗
(self, capacity_bytes: int = (2 << 30))

Source from the content-addressed store, hash-verified

50 """Cache for a llama.cpp model using RAM."""
51
52 def __init__(self, capacity_bytes: int = (2 << 30)):
53 super().__init__(capacity_bytes)
54 self.capacity_bytes = capacity_bytes
55 self.cache_state: OrderedDict[Tuple[int, ...], "llama_cpp.llama.LlamaState"] = (
56 OrderedDict()
57 )
58
59 @property
60 def cache_size(self):

Callers 1

__init__Method · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected