You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* while enabling the use of **less memory** than its alternatives.
30
30
31
-
This enables application and framework developers using similarity search to unleash its performance on Intel®Xeon CPUs (2nd generation and newer).
31
+
This enables application and framework developers using similarity search to unleash its performance on Intel(R) Xeon(R) CPUs (2nd generation and newer).
32
32
33
33
SVS offers a fully-featured and yet simple Python API, compatible with most standard libraries.
34
34
SVS is written in C++ to facilitate its integration into performance-critical applications.
@@ -51,8 +51,8 @@ different configurations of SVS yield significantly increased performance (measu
51
51
SVS is primarily optimized for large-scale similarity search but it still offers [state-of-the-art performance
52
52
at million-scale](https://intel.github.io/ScalableVectorSearch/benchs/static/previous/small_scale_benchs.html).
53
53
54
-
Best performance is obtained with Xeon 6 processors (Granite Rapids), by making use of Intel(R) AVX-512 instructions,
55
-
with excellent results also with 2nd through 5th gen Intel®Xeon® processors (Cascade Lake,
54
+
Best performance is obtained with Intel(R) Xeon(R) 6 processors (Granite Rapids), by making use of Intel(R) AVX-512 instructions,
55
+
with excellent results also with 2nd through 5th gen Intel(R) Xeon(R) processors (Cascade Lake,
56
56
Ice Lake, Sapphire Rapids, and Emerald Rapids).
57
57
58
58
Performance will be degraded if Intel(R) AVX-512 instructions are not available.
0 commit comments