We don't use BLAS. Why? BLAS helps with matrix-matrix multiplications, if you feel lazy and don't want to write the matrix tiling code manually.
They bring essentially nothing of value in vector-vector operations, as compilers can properly auto-vectorize simple dot products... Moreover, they generally only target single and double precision, while we often prefer half or quarter precision. All in all, meaningless dependency.
What do we use? I wrote a tiny package called SimSIMD. It's idea is to utilize less common SIMD instructions, especially in mixed-typed computations, that are hard for compilers to optimize. It was also a fun exercise to evaluate the performance of new SVE instruction on recent Arm CPUs, like the Graviton 3. You can find the code, the benchmarks, and the results in the repo: https://github.com/ashvardanian/simsimd
If you install from PyPi default repository - it comes precompiled, but can still be ad-hoc accelerated with JIT-ed metrics. Either way, it should have decent performance. Still, if you wanna push the limits and work with Multi-Terabyte indexes on one node - recompiling locally should help.
They bring essentially nothing of value in vector-vector operations, as compilers can properly auto-vectorize simple dot products... Moreover, they generally only target single and double precision, while we often prefer half or quarter precision. All in all, meaningless dependency.
What do we use? I wrote a tiny package called SimSIMD. It's idea is to utilize less common SIMD instructions, especially in mixed-typed computations, that are hard for compilers to optimize. It was also a fun exercise to evaluate the performance of new SVE instruction on recent Arm CPUs, like the Graviton 3. You can find the code, the benchmarks, and the results in the repo: https://github.com/ashvardanian/simsimd
Still, even without SimSIMD, USearch seems to be one of the faster implementations of vector search. You can find the benchmarks in the first table here: https://github.com/unum-cloud/usearch#memory-efficiency-down...