CUDA
CUDA is a tool in our research taxonomy.
Related papers
- GPUTOK: GPU Accelerated Byte Level BPE Tokenization
- Exploring Reasoning Reward Model for Agents
- Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra
- KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning
- AviationLMM: A Large Multimodal Foundation Model for Civil Aviation
- TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
- Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs
- Deep-Learning Atlas Registration for Melanoma Brain Metastases: Preserving Pathology While Enabling Cohort-Level Analyses
- Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10
- Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
- CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
- $\texttt{lrnnx}$: A library for Linear RNNs
- TiledAttention: a CUDA Tile SDPA Kernel for PyTorch
- GPU-accelerated simulated annealing based on p-bits with real-world device-variability modeling
- Robo-Saber: Generating and Simulating Virtual Reality Players
- Towards Execution-Grounded Automated AI Research