DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
arXiv e-prints , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
No citing papers match the current filters.