pith. machine review for the scientific record. sign in

Simple linear attention language models balance the recall-throughput tradeoff

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

ACCEPT 1

representative citing papers

KernelBench: Can LLMs Write Efficient GPU Kernels?

cs.LG · 2025-02-14 · accept · novelty 7.0

KernelBench shows that even the best current LLMs generate correct and faster-than-baseline GPU kernels in fewer than 20 percent of realistic ML workloads.

citing papers explorer

Showing 1 of 1 citing paper.

  • KernelBench: Can LLMs Write Efficient GPU Kernels? cs.LG · 2025-02-14 · accept · none · ref 2

    KernelBench shows that even the best current LLMs generate correct and faster-than-baseline GPU kernels in fewer than 20 percent of realistic ML workloads.