Qrita: High-performance Top-k and Top-p Algorithm for GPUs using Pivot-based Truncation and Selection

arXiv:2602.01518 · cs.AI · Submitted 2026-02-02 · Read on arXiv

cs.AI

Submitted: 2026-02-02

Updated: 2026-11-08

Code: https://github.com/vllm-project/vllm

Terminology

Related papers