What is your question? When I use cagre including 100000 number o

A more easier demo to reproduce this bug <div class="snippet-clipboard-content not

[QST] CudaErrorInvalidConfiguration Error when query number is out of 6e4? about raft HOT 3 CLOSED

FakeEnd commented on June 2, 2024

[QST] CudaErrorInvalidConfiguration Error when query number is out of 6e4?

from raft.

Comments (3)

lowener commented on June 2, 2024 2

This issue can be solved by setting the max_queries parameter in cagra.SearchParams().

distances, neighbors = cagra.search(cagra.SearchParams(max_queries=10000),
                                     index, query,
                                     k, handle=handle)

According to the documentation, max_queries is in auto select mode when 0 but it is not bounded (see here). A check should be added.

from raft.

FakeEnd commented on June 2, 2024

A more easier demo to reproduce this bug

batch_size = 1024
n_samples = 200
n_features = 64
# n_queries = 1000
k = 3
dataset = torch.randn(batch_size * n_samples, n_features, dtype=torch.float32).cuda()

handle = DeviceResources()
build_params = cagra.IndexParams(metric="sqeuclidean")

index = cagra.build(build_params, dataset, handle=handle)
distances, neighbors = cagra.search(cagra.SearchParams(),
                                     index, dataset,
                                     k, handle=handle)

from raft.

FakeEnd commented on June 2, 2024

Provide more test example.

This example does computation successfully:

n_features = 64
k = 3
dataset = torch.randn(500000, n_features, dtype=torch.float32).cuda()
query = torch.randn(60000, n_features, dtype=torch.float32).cuda()
handle = DeviceResources()
build_params = cagra.IndexParams(metric="sqeuclidean")

index = cagra.build(build_params, dataset, handle=handle)
distances, neighbors = cagra.search(cagra.SearchParams(),
                                     index, query,
                                     k, handle=handle)

This example fails:

n_features = 64
k = 3
dataset = torch.randn(500000, n_features, dtype=torch.float32).cuda()
query = torch.randn(70000, n_features, dtype=torch.float32).cuda()
handle = DeviceResources()
build_params = cagra.IndexParams(metric="sqeuclidean")

index = cagra.build(build_params, dataset, handle=handle)
distances, neighbors = cagra.search(cagra.SearchParams(),
                                     index, query,
                                     k, handle=handle)

from raft.

Recommend Projects