Tools
Single-shot generation still surfaces net-new kernels with no public reference: NeMo vocab-parallel log-probs, Hyena context parallelism, SA…
Single-shot generation still surfaces net-new kernels with no public reference: NeMo vocab-parallel log-probs, Hyena context parallelism, SAM 3 mask suppression. One GEMM + All-Gather kernel hit 87.9µ
Single-shot generation still surfaces net-new kernels with no public reference: NeMo vocab-parallel log-probs, Hyena context parallelism, SAM 3 mask suppression. One GEMM + All-Gather kernel hit 87.9µs vs 320.6µs for NCCL. PKB is open. Read more and contribute below. Blog: http://www.together.ai/blog/parallelkernelbench Paper: https://www.alphaxiv.org/abs/2606.parallel-kernel-bench Code: https://github.com/uccl-project/mKernel
Source: Together AI (X) | 2026-06-23