| MegaBlocks: Efficient Sparse Training with Mixture-of-Experts | Nov 29, 2022 | GPUMixture-of-Experts | CodeCode Available | 3 | 5 |
| A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models | Oct 17, 2022 | CPUGPU | CodeCode Available | 3 | 5 |
| BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models | Apr 3, 2024 | GPUMath | CodeCode Available | 3 | 5 |
| Merlin: A Vision Language Foundation Model for 3D Computed Tomography | Jun 10, 2024 | 3D Semantic SegmentationComputed Tomography (CT) | CodeCode Available | 3 | 5 |
| mlpack 3: a fast, flexible machine learning library | Jun 18, 2018 | BenchmarkingBIG-bench Machine Learning | CodeCode Available | 3 | 5 |
| MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding | Apr 8, 2024 | GPUMultiple-choice | CodeCode Available | 3 | 5 |
| M+: Extending MemoryLLM with Scalable Long-Term Memory | Feb 1, 2025 | 16kGPU | CodeCode Available | 3 | 5 |
| 94% on CIFAR-10 in 3.29 Seconds on a Single GPU | Mar 30, 2024 | GPU | CodeCode Available | 3 | 5 |
| MagicPIG: LSH Sampling for Efficient LLM Generation | Oct 21, 2024 | CPUGPU | CodeCode Available | 3 | 5 |
| Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray | Feb 7, 2025 | 4kGeneral Knowledge | CodeCode Available | 3 | 5 |
| Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence | Feb 12, 2020 | BIG-bench Machine LearningGPU | CodeCode Available | 3 | 5 |
| LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale | Aug 10, 2024 | GPULanguage Modelling | CodeCode Available | 3 | 5 |
| LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture | Sep 4, 2024 | GPUMamba | CodeCode Available | 3 | 5 |
| LiteGS: A High-Performance Modular Framework for Gaussian Splatting Training | Mar 3, 2025 | 3DGSGPU | CodeCode Available | 3 | 5 |
| EscherNet: A Generative Model for Scalable View Synthesis | Feb 6, 2024 | 3D ReconstructionGPU | CodeCode Available | 3 | 5 |
| LinFusion: 1 GPU, 1 Minute, 16K Image | Sep 3, 2024 | 16kCausal Inference | CodeCode Available | 3 | 5 |
| MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications | Apr 11, 2025 | GPU | CodeCode Available | 3 | 5 |
| LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management | Oct 1, 2024 | GPULanguage Modeling | CodeCode Available | 3 | 5 |
| KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization | Jan 31, 2024 | GPUQuantization | CodeCode Available | 3 | 5 |
| ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters | May 4, 2022 | GPUImitation Learning | CodeCode Available | 3 | 5 |
| Nd-BiMamba2: A Unified Bidirectional Architecture for Multi-Dimensional Data Processing | Nov 22, 2024 | Computational EfficiencyCPU | CodeCode Available | 3 | 5 |
| Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences | Jun 16, 2025 | Document SummarizationGPU | CodeCode Available | 3 | 5 |
| Data Generation for Hardware-Friendly Post-Training Quantization | Oct 29, 2024 | Data AugmentationGPU | CodeCode Available | 3 | 5 |
| Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI | Jul 16, 2025 | GPU | CodeCode Available | 3 | 5 |
| InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation | Sep 12, 2023 | GPUImage Generation | CodeCode Available | 3 | 5 |
