register_cache
Applicable Products
Product |
Supported (√/x) |
|---|---|
√ |
|
√ |
|
√ |
|
x |
|
x |
|
x |
Note: For
Function Description
In the non-PagedAttention scenario, this API is called to register a self-allocated memory.
Prototype
1 | register_cache(cache_desc: CacheDesc, addrs: List[int], cache_keys: Union[Tuple[CacheKey], List[CacheKey]] = (), remote_accessible: Optional[bool] = None) -> Cache: |
Parameters
Parameter |
Data Type |
Value Description |
|---|---|---|
cache_desc |
Cache description. |
|
addrs |
List[int] |
Cache address. The total number of addresses in register_cache and register_blocks_cache cannot exceed 240. |
cache_keys |
Cache index. |
|
remote_accessible |
Optional[bool] |
Whether the registered memory can be used for network transmission. The default value is True for device memory and False for host memory. |
Example
Click GitCode, select the matching version, and obtain the sample from the examples/python directory.
Returns
In normal cases, the registered cache is returned.
If the input data type is incorrect (src and dst do not match), the TypeError or ValueError exception is reported.
If the input parameter is None, the AttributeError exception is reported.
Constraints
The device memory must be registered before link establishment, while the host memory has no restrictions on the order of operations.
The registered memory address must be unique.
A maximum of 50 GB device memory and 20 GB host memory can be registered. Larger registered memory results in higher OS memory usage. This restriction applies to the following products:
Atlas A2 training products /Atlas A2 inference products Atlas A3 training products /Atlas A3 inference products
For D2D data transmission over HCCS, the start address must be aligned to 2 MB; otherwise, the link API may fail. HCCS does not support host memory. This restriction applies to the following products:
Atlas A2 training products /Atlas A2 inference products Atlas A3 training products /Atlas A3 inference products
For RDMA data transmission, host memory must be allocated using the aclrtMallocHost API; otherwise, the link API may fail. This restriction applies to the following products:
Atlas A2 training products /Atlas A2 inference products Atlas A3 training products /Atlas A3 inference products