Papers › Llama 3 Meets MoE: Efficient Upcycling

Llama 3 Meets MoE: Efficient Upcycling

13 Dec 2024arXiv:2412.09952archive 2025-07-28

Aditya Vavre, Ethan He, Dennis Liu, Zijie Yan, June Yang, Nima Tajbakhsh, Ashwath Aithal

Scaling large language models (LLMs) significantly improves performance but comes with prohibitive computational costs. Mixture-of-Experts (MoE) models offer an efficient alternative, increasing capacity without a proportional rise in compute requirements. However, training MoE models from scratch poses challenges like overfitting and routing instability. We present an efficient training recipe leveraging pre-trained dense checkpoints, training an 8-Expert Top-2 MoE model from Llama 3-8B with less than 1% of typical pre-training compute. Our approach enhances downstream performance on academic benchmarks, achieving a 2 improvement in 0-shot accuracy on MMLU, while reaching a Model FLOPs Utilization (MFU) of 46.8 during training using our framework. We also integrate online upcycling in NeMo for seamless use of pre-trained weights, enabling cost-effective development of high-capacity MoE models.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Results from the paper archive 2025-07-28

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections