SNX9
PulseAugur coverage of SNX9 — every cluster mentioning SNX9 across labs, papers, and developer communities, ranked by signal.
-
WiSP enables large MoE models on low-resource GPUs
Researchers have developed WiSP (Working-Set Paging), a novel system designed to enable large Mixture-of-Experts (MoE) models to run on low-resource hardware like a 24GB RTX 3090 GPU. WiSP treats MoE serving as a workin…
-
New pruning methods enhance LLM efficiency by preserving output differences
Researchers have introduced a new family of pruning methods called "difference-informed pruning" designed to improve the efficiency of large language models. These methods focus on preserving the differences between mod…
-
New framework analyzes MAXCUT-based clustering algorithms with theoretical guarantees
This paper introduces a new framework for analyzing three algorithms—SDP1, BalancedSDP, and Spectral clustering—used for partitioning data samples drawn from mixtures of two sub-Gaussian distributions. The researchers p…