RAZZULLIX/fast_topk_batched

High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.

语言：C · GitHub 星标：18 · Fork：2

话题：avx2 · llm-inference · machine-learning · performance · simd · top-k · topk

在 GitHub 上查看原仓库