DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915944826142720 |
|---|---|
| author | Huang, You-Liang Huang, Xinhao Liao, Chengxi Wen, Zeyi |
| author_facet | Huang, You-Liang Huang, Xinhao Liao, Chengxi Wen, Zeyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17709 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models Huang, You-Liang Huang, Xinhao Liao, Chengxi Wen, Zeyi Computation and Language Distributed, Parallel, and Cluster Computing 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. |
| title | DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models |
| topic | Computation and Language Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2604.17709 |