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.
Flying serving: On-the-fly parallelism switching for large language model serving.arXiv preprint arXiv:2602.22593,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Foundry uses template-based CUDA graph context materialization to reduce LLM serving cold-start latency by up to 99% while preserving CUDA graph throughput gains.
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.
-
Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start
Foundry uses template-based CUDA graph context materialization to reduce LLM serving cold-start latency by up to 99% while preserving CUDA graph throughput gains.