Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding
Saved in:
| Published in: | ArXiv cs.AR Recent Papers |
|---|---|
| Format: | Online Article RSS Article |
| Published: |
2026
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1865036767122423813 |
|---|---|
| collection | WordPress RSS FRELIP Feed Integration |
| container_title | ArXiv cs.AR Recent Papers |
| description | |
| discipline_display | Engineering & Technology |
| discipline_facet | Engineering & Technology |
| format | Online Article RSS Article |
| genre | Journal Article |
| id | rss_article:51200 |
| institution | FRELIP |
| journal_source_facet | ArXiv cs.AR Recent Papers |
| publishDate | 2026 |
| publishDateSort | 2026 |
| record_format | rss_article |
| spellingShingle | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding ArXiv cs.AR Recent Papers Chemical Engineering Engineering & Technology |
| sub_discipline_display | Chemical Engineering |
| sub_discipline_facet | Chemical Engineering |
| subject_display | ArXiv cs.AR Recent Papers Chemical Engineering Engineering & Technology ArXiv cs.AR Recent Papers Chemical Engineering Engineering & Technology |
| subject_facet | ArXiv cs.AR Recent Papers Chemical Engineering Engineering & Technology |
| title | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_auth | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_full | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_fullStr | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_full_unstemmed | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_short | 31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding |
| title_sort | 31.1 a 14.08-to-135.69token/s reram-on-logic stacked outlier-free large-language-model accelerator with block-clustered weight-compression and adaptive parallel-speculative-decoding |
| topic | ArXiv cs.AR Recent Papers Chemical Engineering Engineering & Technology |
| url | https://arxiv.org/abs/2605.09375v1 |