Fold-CP: A Context Parallelism Framework for Biomolecular Modeling

TL;DR

Fold-CP is a scalable framework that distributes biomolecular structure prediction across multiple GPUs, enabling modeling of large assemblies beyond previous memory limitations, thus advancing cellular machinery understanding.

Contribution

We introduce a novel context parallelism framework that significantly improves memory efficiency and scalability for large biomolecular structure prediction models.

Findings

Enabled structure prediction of assemblies over 30,000 residues on 64 GPUs.

Achieved over 90% coverage of the CORUM database for complex scoring.

Successfully folded disease-relevant protein complexes with full global context.

Abstract

Understanding cellular machinery requires atomic-scale reconstruction of large biomolecular assemblies. However, predicting the structures of these systems has been constrained by hardware memory requirements of models like AlphaFold 3, imposing a practical ceiling of a few thousand residues that can be processed on a single GPU. Here we present NVIDIA BioNeMo Fold-CP, a context parallelism framework that overcomes this barrier by distributing the inference and training pipelines of co-folding models across multiple GPUs. We use the Boltz models as open source reference architectures and implement custom multidimensional primitives that efficiently parallelize both the dense triangular updates and the irregular, data-dependent pattern of window-batched local attention. Our approach achieves efficient memory scaling; for an N-token input distributed across P GPUs, per-device memory scales as $O(N^2/P)$, enabling the structure prediction of assemblies exceeding 30,000 residues on 64 NVIDIA B300 GPUs. We demonstrate the scientific utility of this approach through successful developer use cases: Fold-CP enabled the scoring of over 90% of Comprehensive Resource of Mammalian protein complexes (CORUM) database, as well as folding of disease-relevant PI4KA lipid kinase complex bound to an intrinsically disordered region without cropping. By providing a scalable pathway for modeling massive systems with full global context, Fold-CP represents a significant step toward the realization of a virtual cell.