ContextQMD
Back to Megatron Lm

Mixture of Experts

docs/user-guide/features/moe.md

23.06662 B
Original Source
<!--- Copyright (c) 2022-2026, NVIDIA CORPORATION. All rights reserved. NVIDIA CORPORATION and its licensors retain all intellectual property and proprietary rights in and to this software, related documentation and any modifications thereto. Any use, reproduction, disclosure or distribution of this software and related documentation without an express license agreement from NVIDIA CORPORATION is strictly prohibited. -->

Mixture of Experts

{toctree}
:maxdepth: 1
:caption: MoE Features

multi_token_prediction
multi_latent_attention
../../api-guide/router_replay
{include}