copy_blocks

Applicable Products

Product	Supported (√/x)
Ascend 950PR/Ascend 950DT	x
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	x
Atlas inference products	x
Atlas training products	x

Note: For 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

Copies blocks in the PagedAttention scenario.

Prototype

copy_blocks(cache: Cache, copy_block_info: Dict[int, List[int]])

Parameters

Parameter	Data Type	Value Description
cache	Cache	Target cache.
copy_block_info	Dict[int, List[int]]	A dictionary mapping original block indices to lists of target block indices.

Example

cache_manager.copy_blocks(cache, {1: [2,3]})

Returns

In normal cases, no value is returned.

If the input data type is incorrect, the TypeError or ValueError exception is reported.

If the execution time exceeds the value of sync_kv_timeout, an LLMException is thrown.

Constraints

None

Parent topic: CacheManager (to Be Deprecated)