Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.
Deja vu: Contextual sparsity for efficient LLMs at inference time
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.