{"total":24,"rows":[{"id":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"area":null},{"id":"2402.10930","title":"ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters","created":"2024-01-31","cited_by_count":14,"area":null},{"id":"2209.00606","title":"Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation","created":"2022-09-01","cited_by_count":12,"area":null},{"id":"2302.08005","title":"Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2503.16709","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","created":"2025-03-20","cited_by_count":8,"area":null},{"id":"2404.11788","title":"Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2405.06626","title":"Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2507.11331","title":"SystolicAttention: Fusing FlashAttention within a Single Systolic Array","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2306.17266","title":"Subgraph Stationary Hardware-Software Inference Co-Design","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2504.06531","title":"Beyond Moore's Law: Harnessing the Redshift of Generative AI with Effective Hardware-Software Co-Design","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.03745","title":"AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2510.25166","title":"A Study on Inference Latency for Vision Transformers on Mobile Devices","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2601.20317","title":"VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2410.00273","title":"Comprehensive Performance Modeling and System Design Insights for Foundation Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2411.14733","title":"FLARE: FP-Less PTQ and Low-ENOB ADC Based AMS-PiM for Error-Resilient, Fast, and Efficient Transformer Acceleration","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2411.17720","title":"MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2506.06095","title":"Accelerating Sparse Transformer Inference on GPU","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2512.07312","title":"DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Management","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2602.11016","title":"From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.10026","title":"RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.17653","title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.11211","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.23582","title":"Transformer Accelerator (TFA): A Macro-Op INT8 Hardware Chip for Transformer Inference and Machine Translation","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}