极速阅览

Python module: cuvs.neighbors.mg.ivf_flat

Index

1	cdef class Index

Multi-GPU IVF-Flat index object. Stores the trained multi-GPU IVF-Flat index state which can be used to perform nearest neighbors searches across multiple GPUs.

Members

NameKind

trained

property

trained

1	def trained(self)

IndexParams

1	cdef class IndexParams(SingleGpuIndexParams)

Parameters to build multi-GPU IVF-Flat index for efficient search. Extends single-GPU IndexParams with multi-GPU specific parameters.

Parameters

NameTypeDescription

distribution_mode	str, default = "sharded"	Distribution mode for multi-GPU setup. Valid values: [“replicated”, “sharded”]
**kwargs	Additional parameters passed to single-GPU IndexParams

Constructor

1	def __init__(self, , distribution_mode="sharded", *kwargs)

Members

NameKind

get_handle	method
distribution_mode	property

get_handle

1	def get_handle(self)

distribution_mode

1	def distribution_mode(self)

SearchParams

1	cdef class SearchParams(SingleGpuSearchParams)

Parameters to search multi-GPU IVF-Flat index.

Constructor

def __init__(self, *, n_probes=1, search_mode="load_balancer", merge_mode="merge_on_root_rank", n_rows_per_batch=1000, **kwargs)

Members

NameKind

get_handle	method
search_mode	property
search_mode	method
merge_mode	property
merge_mode	method
n_rows_per_batch	property
n_rows_per_batch	method

get_handle

1	def get_handle(self)

search_mode

1	def search_mode(self)

Get the search mode for multi-GPU search.

search_mode

1	def search_mode(self, value)

Set the search mode for multi-GPU search.

merge_mode

1	def merge_mode(self)

Get the merge mode for multi-GPU search.

merge_mode

1	def merge_mode(self, value)

Set the merge mode for multi-GPU search.

n_rows_per_batch

1	def n_rows_per_batch(self)

Get the number of rows per batch for multi-GPU search.

n_rows_per_batch

1	def n_rows_per_batch(self, value)

Set the number of rows per batch for multi-GPU search.

build

@auto_sync_multi_gpu_resources

1	def build(IndexParams index_params, dataset, resources=None)

Build the multi-GPU IVF-Flat index from the dataset for efficient search.

Parameters

NameTypeDescription

index_params	cuvs.neighbors.ivf_flat.IndexParams
dataset	Array interface compliant matrix shape (n_samples, dim)	Supported dtype [float32, float16, int8, uint8] IMPORTANT: For multi-GPU IVF-Flat, the dataset MUST be in host memory (CPU). If using CuPy/device arrays, transfer to host with array.get() or cp.asnumpy(array).
resources	cuvs.common.Resources, optional

Returns

NameTypeDescription

index

cuvs.neighbors.ivf_flat.Index

Examples

>>> import numpy as np
>>> from cuvs.neighbors.mg import ivf_flat
>>> n_samples = 50000
>>> n_features = 50
>>> n_queries = 1000
>>> k = 10
>>> # For multi-GPU IVF-Flat, use host (NumPy) arrays
>>> dataset = np.random.random_sample((n_samples, n_features)).astype(
...     np.float32)
>>> build_params = ivf_flat.IndexParams(metric="sqeuclidean")
>>> index = ivf_flat.build(build_params, dataset)
>>> distances, neighbors = ivf_flat.search(
...     ivf_flat.SearchParams(),
...     index, dataset, k)
>>> # Results are already in host memory (NumPy arrays)

extend

@auto_sync_multi_gpu_resources

1	def extend(Index index, new_vectors, new_indices=None, resources=None)

Extend the multi-GPU IVF-Flat index with new vectors.

Parameters

NameTypeDescription

index	cuvs.neighbors.ivf_flat.Index
new_vectors	Array interface compliant matrix shape (n_new_vectors, dim)	Supported dtype [float32, float16, int8, uint8] IMPORTANT: For multi-GPU IVF-Flat, new_vectors MUST be in host memory (CPU). If using CuPy/device arrays, transfer to host with array.get() or cp.asnumpy(array).
new_indices	Array interface compliant matrix shape (n_new_vectors,)	, optional If provided, these indices will be used for the new vectors. If not provided, indices will be automatically assigned. IMPORTANT: Must be in host memory (CPU) for multi-GPU IVF-Flat.
resources	cuvs.common.Resources, optional

Examples

>>> import numpy as np
>>> from cuvs.neighbors.mg import ivf_flat
>>> n_samples = 50000
>>> n_features = 50
>>> n_new_vectors = 1000
>>> # For multi-GPU IVF-Flat, use host (NumPy) arrays
>>> dataset = np.random.random_sample((n_samples, n_features)).astype(
...     np.float32)
>>> new_vectors = np.random.random_sample(
...     (n_new_vectors, n_features)).astype(np.float32)
>>> new_indices = np.arange(n_samples, n_new_vectors, dtype=np.int64)
>>> build_params = ivf_flat.IndexParams(metric="sqeuclidean")
>>> index = ivf_flat.build(build_params, dataset)
>>> ivf_flat.extend(index, new_vectors, new_indices)

search

@auto_sync_multi_gpu_resources @auto_convert_output

def search(SearchParams search_params, Index index, queries, k, neighbors=None, distances=None, resources=None)

Search the multi-GPU IVF-Flat index for the k-nearest neighbors of each query.

Parameters

NameTypeDescription

search_params	cuvs.neighbors.ivf_flat.SearchParams
index	cuvs.neighbors.ivf_flat.Index
queries	Array interface compliant matrix shape (n_queries, dim)	Supported dtype [float32, float16, int8, uint8] IMPORTANT: For multi-GPU IVF-Flat, queries MUST be in host memory (CPU). If using CuPy/device arrays, transfer to host with array.get() or cp.asnumpy(array).
k	int	The number of neighbors to search for each query.
neighbors	Array interface compliant matrix shape (n_queries, k), optional	If provided, this array will be filled with the indices of the k-nearest neighbors. If not provided, a new host array will be allocated. IMPORTANT: Must be in host memory (CPU) for multi-GPU IVF-Flat.
distances	Array interface compliant matrix shape (n_queries, k), optional	If provided, this array will be filled with the distances to the k-nearest neighbors. If not provided, a new host array will be allocated. IMPORTANT: Must be in host memory (CPU) for multi-GPU IVF-Flat.
resources	cuvs.common.Resources, optional

Returns

NameTypeDescription

distances	numpy.ndarray	The distances to the k-nearest neighbors for each query (in host memory).
neighbors	numpy.ndarray	The indices of the k-nearest neighbors for each query (in host memory).

Examples

>>> import numpy as np
>>> from cuvs.neighbors.mg import ivf_flat
>>> n_samples = 50000
>>> n_features = 50
>>> n_queries = 1000
>>> k = 10
>>> # For multi-GPU IVF-Flat, use host (NumPy) arrays
>>> dataset = np.random.random_sample((n_samples, n_features)).astype(
...     np.float32)
>>> queries = np.random.random_sample((n_queries, n_features)).astype(
...     np.float32)
>>> build_params = ivf_flat.IndexParams(metric="sqeuclidean")
>>> index = ivf_flat.build(build_params, dataset)
>>> distances, neighbors = ivf_flat.search(
...    ivf_flat.SearchParams(),
...    index, queries, k)
>>> # Results are already in host memory (NumPy arrays)

save

@auto_sync_multi_gpu_resources

1	def save(Index index, filename, resources=None)

Serialize the multi-GPU IVF-Flat index to a file.

Parameters

NameTypeDescription

index	cuvs.neighbors.ivf_flat.Index
filename	str	The filename to serialize the index to.
resources	cuvs.common.Resources, optional

Examples

>>> import numpy as np
>>> from cuvs.neighbors.mg import ivf_flat
>>> n_samples = 50000
>>> n_features = 50
>>> # For multi-GPU IVF-Flat, use host (NumPy) arrays
>>> dataset = np.random.random_sample((n_samples, n_features)).astype(
...     np.float32)
>>> build_params = ivf_flat.IndexParams(metric="sqeuclidean")
>>> index = ivf_flat.build(build_params, dataset)
>>> ivf_flat.save(index, "index.bin")

load

@auto_sync_multi_gpu_resources

1	def load(filename, resources=None)

Deserialize the multi-GPU IVF-Flat index from a file.

Parameters

NameTypeDescription

filename	str	The filename to deserialize the index from.
resources	cuvs.common.Resources, optional

Returns

NameTypeDescription

index

Index

The deserialized index.

Examples

>>> from cuvs.neighbors.mg import ivf_flat
>>> index = ivf_flat.load("index.bin")  # doctest: +SKIP

distribute

@auto_sync_multi_gpu_resources

1	def distribute(filename, resources=None)

Distribute a single-GPU IVF-Flat index across multiple GPUs from a file.

Parameters

NameTypeDescription

filename	str	The filename to distribute the index from.
resources	cuvs.common.Resources, optional

Returns

NameTypeDescription

index

Index

The distributed index.

Examples

>>> from cuvs.neighbors.mg import ivf_flat
>>> index = ivf_flat.distribute("single_gpu_index.bin")  # doctest: +SKIP

Multi-GPU IVF Flat

Index

trained

IndexParams

get_handle

distribution_mode

SearchParams

get_handle

search_mode

search_mode

merge_mode

merge_mode

n_rows_per_batch

n_rows_per_batch

build

extend

search

save

load

distribute

Neighbors Multi GPU Cagra

Neighbors Multi GPU IVF PQ

1	>>> import numpy as np
2	>>> from cuvs.neighbors.mg import ivf_flat
3	>>> n_samples = 50000
4	>>> n_features = 50
5	>>> n_queries = 1000
6	>>> k = 10
7	>>> # For multi-GPU IVF-Flat, use host (NumPy) arrays
8	>>> dataset = np.random.random_sample((n_samples, n_features)).astype(
9	... np.float32)
10	>>> build_params = ivf_flat.IndexParams(metric="sqeuclidean")
11	>>> index = ivf_flat.build(build_params, dataset)
12	>>> distances, neighbors = ivf_flat.search(
13	... ivf_flat.SearchParams(),
14	... index, dataset, k)
15	>>> # Results are already in host memory (NumPy arrays)

1	>>> from cuvs.neighbors.mg import ivf_flat
2	>>> index = ivf_flat.load("index.bin") # doctest: +SKIP

1	>>> from cuvs.neighbors.mg import ivf_flat
2	>>> index = ivf_flat.distribute("single_gpu_index.bin") # doctest: +SKIP