A Review on Proprietary Accelerators for Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929757065576448 |
|---|---|
| author | Park, Sihyeong Lee, Jemin Kim, Byung-Soo Jeon, Seokhun |
| author_facet | Park, Sihyeong Lee, Jemin Kim, Byung-Soo Jeon, Seokhun |
| contents | With the advancement of Large Language Models (LLMs), the importance of accelerators that efficiently process LLM computations has been increasing. This paper discusses the necessity of LLM accelerators and provides a comprehensive analysis of the hardware and software characteristics of the main commercial LLM accelerators. Based on this analysis, we propose considerations for the development of next-generation LLM accelerators and suggest future research directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09650 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Review on Proprietary Accelerators for Large Language Models Park, Sihyeong Lee, Jemin Kim, Byung-Soo Jeon, Seokhun Performance Hardware Architecture With the advancement of Large Language Models (LLMs), the importance of accelerators that efficiently process LLM computations has been increasing. This paper discusses the necessity of LLM accelerators and provides a comprehensive analysis of the hardware and software characteristics of the main commercial LLM accelerators. Based on this analysis, we propose considerations for the development of next-generation LLM accelerators and suggest future research directions. |
| title | A Review on Proprietary Accelerators for Large Language Models |
| topic | Performance Hardware Architecture |
| url | https://arxiv.org/abs/2503.09650 |