Preprint
Aug 2026
Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget
Tevatron 3.0 is presented, which integrates a Megatron-Core training backend into Tevatron while preserving its data pipeline, evaluation workflow, and Hugging Face-compatible checkpoints, and supports both LoRA and full-parameter fine-tuning.
Zhichao Xu, Xueguang Ma, Shengyao Zhuang et al.
· 2 citations