High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.
-
Updated
Mar 20, 2026 - C
High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.
Final project of "Algorithms and Principles of Computer Science" course - "Prova finale di Algoritmi e Principi dell'informatica" - Politecnico di Milano - A.A. 2020-2021
Add a description, image, and links to the top-k topic page so that developers can more easily learn about it.
To associate your repository with the top-k topic, visit your repo's landing page and select "manage topics."