KernelAgent: Hardware-Guided GPU Kernel Optimization via Multi-Agent Orchestration
Kaiming Cheng of Meta will present “KernelAgent: Hardware-Guided GPU Kernel Optimization via Multi-Agent Orchestration” at PyTorch Conference North America 2026. The session will cover how KernelAgent adds a hardware-guided optimization layer that integrates GPU hardware-performance signals into a closed-loop multi-agent workflow for Triton kernels. Across all 100 KernelBench L1 tasks evaluated, KernelAgent achieved a 2.02x speedup over kernels generated by earlier versions and an average 1.56x speedup compared with default torch.compile. Register for PyTorch Conference North America 2026: h