KernelMosaic: An Open Dataset and Agentic Framework for CUDA Kernel Generation
cs.LG, cs.AI
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/ggml-org/llama.cpp
Terminology
Sources
- CUDA-LLM: LLMs Can Write Efficient CUDA Kernels
- CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
- CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
- ConCuR: Conciseness Makes State-of-the-Art Kernel Generation
- AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
- Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
- Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis