tensor_addrs

Applicability

Note: For the Atlas A2 training products/Atlas A2 inference products, only the Atlas 800I A2 inference server, Atlas 300I A2 inference card, and A200I A2 Box heterogeneous components are supported.

Function Description

Obtains the cache address.

Prototype

1
2

@property
tensor_addrs() -> List[int]

Parameters

None

Example

1
2
3

...
kv_cache = cache_manager.allocate_cache(cache_desc, cache_keys)
print(kv_cache.tensor_addrs)

Returns

In normal cases, an address of the Cache type is returned.

Restrictions

None