FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
A method for the construction of minimum- redundancy codes.Proceedings of the IRE, 40(9):1098–1101
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2representative citing papers
TStore reduces AI model storage via tensor-level fingerprinting, clustering, and compression without annotations while claiming to preserve usability.
citing papers explorer
-
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
-
TStore: Rethinking AI Model Hub with Tensor-Centric Compression
TStore reduces AI model storage via tensor-level fingerprinting, clustering, and compression without annotations while claiming to preserve usability.