titleTPHC: Improving Hyper-Connections with Tensor-Parallel Grouped Updates
authorsXinying Hu, You Wu, Haoyi Wu, Jianchao Tan, Kefeng Zhang, Yuchen Xie, Kewei Tu
date2026-11-17
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.23026
upvotes2 (Hugging Face Daily Papers, 2026-11-19)
linksabs pdf hf code
cite
abstractHyper-Connections (HC) expand the residual stream of a Transformer into N parallel streams, and manifold-constrained HC (mHC) stabilizes them at scale. However, mHC benefits little from more than four streams, partly because each sublayer writes a single output to all streams, limiting how differently they can be updated. In this work, we propose TPHC, which integrates tensor-parallel (TP) shards with HC streams to promote greater independence across streams. Specifically, we route a separate mixture of the residual streams to each TP shard and keep the individual shard outputs separate during write-back, so each stream can receive a different mixture of those outputs. This design makes the residual-stream updates more expressive without adding parameters or FLOPs to the attention or FFN sublayers. With native support for stream sharding under TP, TPHC requires only 9% more training time than mHC on an 8B model when both use four streams. Increasing the number of streams from four to sixteen raises its training time by only 19%. On a 1.1B model trained on 100B tokens, TPHC reduces validation loss by 0.7-1.0% and raises average zero-shot accuracy across six commonsense reasoning benchmarks by 0.3-0.7 percentage points relative to mHC at matched stream counts Nin{4,8,16}. Our code is available at https://github.com/wuyou2002/TPHC.

bibtex

@misc{hu2026tphc,
  title={TPHC: Improving Hyper-Connections with Tensor-Parallel Grouped Updates},
  author={Xinying Hu and You Wu and Haoyi Wu and Jianchao Tan and Kefeng Zhang and Yuchen Xie and Kewei Tu},
  year={2026},
  eprint={2611.23026},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.23026}
}