Research
DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel
arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel inference performance when trying to scale up the model size. To mitigate this important performance issue, this paper introduces DeInfer, a high-performance inference system dedicated to parallel inference of decomposed LLMs. It consists of multiple optimizations to maximize performance and be compatible with state-of-the-art optimization techniques. Extensive experiments are carried out to evaluate DeInfer's performance, where the results demonstrate its superiority, suggesting it can greatly facilitate the parallel inference of decomposed LLMs.
Related
- STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning
- Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
- Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation
- DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Source: arXiv cs.CL | 2026-04-21