cache_desc

Applicable Products

Product	Supported (Yes/No)
Ascend 950PR/Ascend 950DT	No
Atlas A3 training products/Atlas A3 inference products	Yes
Atlas A2 training products/Atlas A2 inference products	Yes
Atlas 200I/500 A2 inference products	No
Atlas inference products	No
Atlas training products	No

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

Function Description

Obtains the KV cache description.

Prototype

@property
cache_desc() -> CacheDesc

Parameters

None

Example

...
kv_cache = kv_cache_manager.allocate_cache(cache_desc, cache_keys)
print(kv_cache.cache_desc.num_tensors)

Returns

In normal cases, the cache description of the KvCache type is returned.

Constraints

None

Parent topic: KvCache