Popular repositories Loading
-
fast_topk_batched
fast_topk_batched Public🚀 Accelerate CPU inference with Fast TopK for high-performance batched Top-K selection, optimized for efficient LLM sampling workloads.
C++
-
chrispion.github.io
chrispion.github.io Public⚡ Accelerate batched Top-K selection for CPU inference, optimizing LLM sampling workloads with performance up to 80x faster than PyTorch.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.