-
## Description:
For the JDS sparse matrix solver, managing the storage, retrieval, and conversion of data is very important. This issue is to write a unit test for the storage mechanisms of the JDS …
-
To get an overview which things we are missing with staying using/being compatible to older Java versions,
and determine the right point of time when its maybe worth to drop one or find a way to work…
-
Starting off, we'd like to express our appreciacion for the project.
Integrating the following operations for sparse vectors would be of great use to our use case:
- An aggregate sum operation fo…
-
Hello! I see many articles (like pinecones) that use the following ways to combine the hybrid search results from dense vector and splade.
However i'm a bit confused of how it would work if the d…
-
All existing metrics imply dense vector representations. Dealing with very high-dimensional vectors, sparse representations may provide huge space-efficiency gains.
The only operation that needs to …
-
I want to understand the overall framework technically. From my understanding and from reading the paper, you are training vectors of shape [input_hidden, 1]—for example, [384, 1] in the case of ViT S…
-
By default k-NN plugin uses dense vector for Cosine similarity measure. NMS library has support for sparse vector space type. We could enable this support in k-NN plugin.
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Is your feature request related to a problem? Please describe.
Now milvus supports only dense vectors and lack…
-
Today we keep the local storage segment index state comprises of various metadata values, and three vectors (for offsets, file position, timestamp) that serve as a sparse index into the segment file. …
-
Hello,
Thanks for the great library!
I am trying to perform the eigendecomposition of a torch LazyTensor. The following is a slight adaptation of the code in https://www.kernel-operations.io/keop…