krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-04 18:38:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update qdrant-landing/content/blog/qdrant-1.14.x.md

Browse Source 
Co-authored-by: Tim Visée <tim@visee.me>
This commit is contained in:
David Myriel
2025-03-25 17:10:18 +01:00
committed by GitHub
co-authored by Tim Visée
parent e5bf677ec1
commit c5ed43c376
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/qdrant-1.14.x.md
+1 -1
View File
@@ -132,7 +132,7 @@ Qdrant now **saturates CPU and disk IO** more effectively in parallel when optim
This leads to **faster optimizations**, which are specially noticeable on large machines handling big data movement.
It also gives you **predictable performance**, as there are fewer sudden spikes or slowdowns during indexing and merging operations.
**Figure 1:** Indexing 400 million vectors - CPU and disk usage profiles.
**Figure 1:** Indexing 400 million vectors - CPU and disk usage profiles. Previous Qdrant version on the left, new Qdrant version on the right.
![indexation-improvement](/blog/qdrant-1.14.x/indexation.png)
**Observed Results:** The improvement is especially noticeable during large-scale indexing. In our experiment, **we indexed 400 million 512-dimensional vectors**. The previous version of Qdrant took around 40 hours on an 8-core machine, while the development version with this change completed the task in just 28 hours.