AI as a Compiler: Compiling Triton kernels without the Triton compiler
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/NVIDIA/cutlass
Sources
- Dion: Distributed Orthonormalized Updates
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Tawa: Automatic Warp Specialization for Modern GPUs with Asynchronous References
- TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
- CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
- Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- HipKittens: Fast and Furious AMD Kernels
- MLIR: A Compiler Infrastructure for the End of Moore's Law
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
- Forgetting Transformer: Softmax Attention with a Forget Gate
- BitDelta: Your Fine-Tune May Only Be Worth One Bit
- Learning to Combine Instructions in LLVM Compiler
- Stochastic Superoptimization
- ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
- TileLang: A Composable Tiled Programming Model for AI Systems
- SuperCoder: Assembly Program Superoptimization with Large Language Models
- PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX
- KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems