FlexMoE produces nested pruned subnetworks for MoE LLMs across budgets via channel importance ranking and discrete action learning, plus one mid-budget recovery fine-tune, retaining 99.8% performance at 50% expert parameter pruning.
OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfigura- tion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Dual-pool token-budget routing for LLM serving reduces GPU-hours by 31-42% and preemption rates by 5.4x through online-learned request classification without a tokenizer.
citing papers explorer
-
FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
FlexMoE produces nested pruned subnetworks for MoE LLMs across budgets via channel importance ranking and discrete action learning, plus one mid-budget recovery fine-tune, retaining 99.8% performance at 50% expert parameter pruning.
-
Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
Dual-pool token-budget routing for LLM serving reduces GPU-hours by 31-42% and preemption rates by 5.4x through online-learned request classification without a tokenizer.