Latent-MoE
Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.…
aiattentioncudak3kimillm
More Everything else
Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.…