DRTriton: Large-Scale Synthetic Data Reinforcement Learning for Triton Kernel Generation

Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent researches leverage Large Language Models (LLMs) to automatically convert PyTorch refer…

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agen…

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

Memory access errors remain one of the most pervasive bugs in GPU programming. Existing GPU sanitizers such as compute-sanitizer detect memory access errors by instrumenting every memory instructio…

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

As agentic AI systems become increasingly capable of generating and optimizing GPU kernels, progress is constrained by benchmarks that reward speedup over software baselines rather than proximity t…

Topicbox

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs. To address this challenge and democrati…

Running LLM Inference on Kubernetes: What Breaks First

Learn the critical failure points when running LLM inference on Kubernetes, including resource constraints, operator compatibility, security, scalability, and monitoring best practices for production workloads.

Github Awesome (@GithubAwesome) on X

Building AI models and tired of staring at GPU profilers? AutoKernel does it for you. Inspired by Karpathy's autoresearch, it brings autonomous AI agents to GPU kernel optimization. Point it at any PyTorch model, go to sleep, and wake up to optimized Triton kernels. It