DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
cs.CL, cs.LG
Submitted: 2026-03-23
Updated: 2026-11-12
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
- DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
- TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization
- AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
- KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
- WizardCoder: Empowering Code Large Language Models with Evol-Instruct
- KernelBench: Can LLMs Write Efficient GPU Kernels?
- Code Llama: Open Foundation Models for Code
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks
- DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
- Astra: A Multi-Agent System for GPU Kernel Performance Optimization
- Magicoder: Empowering Code Generation with OSS-Instruct
- TritonRL: Training LLMs to Think and Code Triton Without Cheating
- CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data