| FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving | Nov 27, 2024 | FairnessGPU | CodeCode Available | 7 |
| xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism | Nov 4, 2024 | GPU | CodeCode Available | 7 |
| ThunderKittens: Simple, Fast, and Adorable AI Kernels | Oct 27, 2024 | GPUState Space Models | CodeCode Available | 7 |
| D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement | Oct 17, 2024 | GPUReal-Time Object Detection | CodeCode Available | 7 |
| Pyramidal Flow Matching for Efficient Video Generative Modeling | Oct 8, 2024 | GPUText-to-Video Generation | CodeCode Available | 7 |
| ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI | Oct 1, 2024 | GPUImitation Learning | CodeCode Available | 7 |
| Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving | Jun 24, 2024 | CPUGPU | CodeCode Available | 7 |
| Scalable MatMul-free Language Modeling | Jun 4, 2024 | GPULanguage Modeling | CodeCode Available | 7 |
| Mirage: A Multi-Level Superoptimizer for Tensor Programs | May 9, 2024 | GPUNavigate | CodeCode Available | 7 |
| Labeling supervised fine-tuning data with the scaling law | May 5, 2024 | coreference-resolutionCoreference Resolution | CodeCode Available | 7 |
| Fast Timing-Conditioned Latent Audio Diffusion | Feb 7, 2024 | Audio GenerationGPU | CodeCode Available | 7 |
| PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models | Jan 10, 2024 | GPUImage Generation | CodeCode Available | 7 |
| Elixir: Train a Large Language Model on a Small GPU Cluster | Dec 10, 2022 | CPUGPU | CodeCode Available | 7 |
| GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers | Oct 31, 2022 | GPULanguage Modelling | CodeCode Available | 7 |
| YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors | Jul 6, 2022 | 2D Object DetectionGPU | CodeCode Available | 7 |
| LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models | Sep 21, 2023 | 4kGPU | CodeCode Available | 6 |
| FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning | Jul 17, 2023 | GPULanguage Modeling | CodeCode Available | 6 |
| SqueezeLLM: Dense-and-Sparse Quantization | Jun 13, 2023 | GPUQuantization | CodeCode Available | 6 |
| QLoRA: Efficient Finetuning of Quantized LLMs | May 23, 2023 | ChatbotGPU | CodeCode Available | 6 |
| FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness | May 27, 2022 | 16k4k | CodeCode Available | 6 |
| Group-in-Group Policy Optimization for LLM Agent Training | May 16, 2025 | GPUMathematical Reasoning | CodeCode Available | 5 |
| MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention | Apr 22, 2025 | GPU | CodeCode Available | 5 |
| Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts | Feb 27, 2025 | Computational EfficiencyGPU | CodeCode Available | 5 |
| Representing Long Volumetric Video with Temporal Gaussian Hierarchy | Dec 12, 2024 | GPU | CodeCode Available | 5 |
| DEIM: DETR with Improved Matching for Fast Convergence | Dec 5, 2024 | Data AugmentationGPU | CodeCode Available | 5 |
