GPU Index Out of Bounds Error During Vector Search in RAG Module #1437

Closed
opened 2025-11-11 14:45:15 -06:00 by GiteaMirror · 0 comments
Owner

Originally created by @Belonger on GitHub (Jul 5, 2024).

Description:

When using the RAG module, I stored a total of 1300 files, amounting to 90,701,824 characters. During the vector search process (selecting 1300 files for search), an index out-of-bounds bug occurred. The specific error is:

../aten/src/ATen/native/cuda/Indexing.cu:1289: indexSelectLargeIndex: block: [689,0,0], thread: [96,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
../aten/src/ATen/native/cuda/Indexing.cu:1289: indexSelectLargeIndex: block: [689,0,0], thread: [97,0,0] Assertion `srcIndex < srcSelectDimSize` failed.
......

This happens during the vector search on the GPU, and there is still plenty of memory available during the search process.

How is this error triggered, and how can it be resolved?

Originally created by @Belonger on GitHub (Jul 5, 2024). Description: When using the RAG module, I stored a total of 1300 files, amounting to 90,701,824 characters. During the vector search process (selecting 1300 files for search), an index out-of-bounds bug occurred. The specific error is: ``` ../aten/src/ATen/native/cuda/Indexing.cu:1289: indexSelectLargeIndex: block: [689,0,0], thread: [96,0,0] Assertion `srcIndex < srcSelectDimSize` failed. ../aten/src/ATen/native/cuda/Indexing.cu:1289: indexSelectLargeIndex: block: [689,0,0], thread: [97,0,0] Assertion `srcIndex < srcSelectDimSize` failed. ...... ``` This happens during the vector search on the GPU, and there is still plenty of memory available during the search process. How is this error triggered, and how can it be resolved?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#1437