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.

1 best points · 0 comments · 1 Hacker News post · 18 GitHub stars · View on GitHub

Hacker News discussions

• Fast_topk_batched: High-performance batched Top-K selection for CPU inference (1 points, 0 comments, by thunderbong, 2026-01-19)