[IEEE] APTQ+: Attention-FFN-aware Post-Training Quantization for a Layer-wise LLM Accelerator on FPGA |
|
This post will be closed automatically in 2026-09-17 20:49
Reward30points
|
| |
post
reply
points
450
30
Runtime Threshold Signature-Based Unmanned Aerial Vehicle Swarm Authentication With Autonomous Splitting Support
30
Comparative Study of Different Machine Learning Models for Customer Churn Analysis Using SMOTE and Feature Variation Along With Customer Segmentation
30
Setting Up A CICD Pipeline in The Cloud for A Web Application
40
[Other]Multi-Scale Hourly Electrical Load Dataset for AI-Driven Data Centers: Active and Reactive Power from CPU/GPU to Facility Level
