Accelerating Large Language Model Inference via Early-Exiting Algorithms
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908707860774912 |
|---|---|
| author | Bae, Sangmin |
| author_facet | Bae, Sangmin |
| contents | Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce a fundamental conflict: the per-token dynamism intended to save computation often creates system-level bottlenecks that can paradoxically reduce throughput in batched inference. This dissertation resolves this conflict by co-designing adaptive algorithms and model architectures to strike an optimal balance between dynamism and efficiency. To this end, our work first addresses critical sources of overhead in conventional early-exiting by proposing an efficient parallel decoding mechanism. We then show that deep parameter sharing provides an architectural foundation that not only yields compact, parameter-efficient models but also inherently mitigates the critical synchronization issues affecting dynamic inference. Finally, this work presents a unified framework where lightweight routers are pretrained to dynamically assign an optimal recursion depth for each token. This approach establishes a new Pareto frontier between efficiency and performance by effectively optimizing for both adaptive computation and parameter efficiency within a single model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05915 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating Large Language Model Inference via Early-Exiting Algorithms Bae, Sangmin Computation and Language Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce a fundamental conflict: the per-token dynamism intended to save computation often creates system-level bottlenecks that can paradoxically reduce throughput in batched inference. This dissertation resolves this conflict by co-designing adaptive algorithms and model architectures to strike an optimal balance between dynamism and efficiency. To this end, our work first addresses critical sources of overhead in conventional early-exiting by proposing an efficient parallel decoding mechanism. We then show that deep parameter sharing provides an architectural foundation that not only yields compact, parameter-efficient models but also inherently mitigates the critical synchronization issues affecting dynamic inference. Finally, this work presents a unified framework where lightweight routers are pretrained to dynamically assign an optimal recursion depth for each token. This approach establishes a new Pareto frontier between efficiency and performance by effectively optimizing for both adaptive computation and parameter efficiency within a single model. |
| title | Accelerating Large Language Model Inference via Early-Exiting Algorithms |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.05915 |