{"total":18,"rows":[{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2412.03317","title":"FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2505.13813","title":"FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2505.19349","title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2412.14775","title":"Energy and polarization based on-line interference mitigation in radio interferometry","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2508.19087","title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2606.08761","title":"APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2609.12923","title":"Dissecting GPU Utilization for LLM Inference on Nvidia Hopper","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2410.22249","title":"Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2506.22818","title":"TriADA: Massively Parallel Trilinear Matrix-by-Tensor Multiply-Add Algorithm and Device Architecture for the Acceleration of 3D Discrete Transformations","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2602.12962","title":"TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.25692","title":"A Unified Memory Perspective for Probabilistic Trustworthy AI","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2608.14550","title":"FLOPs vs Real Work: The Importance of Replication in AI Efficiency Assessment","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2608.24664","title":"Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}