Horace He

AI Compiler Architect

Sources checked
ABOUT

AI Compiler Architect at Thinking Systems and former core team member of PyTorch at Meta AI. Co-creator of PyTorch 2.0 (`torch.compile`), TorchDynamo, and TorchInductor, transforming dynamic Python execution into high-performance fused Triton kernels.

Areas of focus

Professional niches

THE WORK BEHIND THE PROFILE

Proof of Work

researchChecked Sep 22, 2026

PyTorch 2: Dynamic Python Bytecode Compilation and TorchInductor

Co-authored the ACM ASPLOS 2024 paper detailing TorchDynamo and TorchInductor, which intercept Python frame evaluation bytecodes to capture computational graphs safely and generate fused Triton GPU kernels with 0% code modifications.

Scope & limitations

Dynamic control flow with non-tensor Python data structures forces graph breaks that require partial eager execution fallback.

Context: TorchDynamo, TorchInductor, OpenAI Triton backend, 160+ benchmark models.

View mission
explanationChecked Sep 22, 2026

Making Deep Learning Go Brrrr: Performance Engineering and GPU Kernel Optimization

Authored the definitive technical guide on GPU architecture, memory hierarchy, arithmetic intensity, and operator fusion, read by hundreds of thousands of AI infrastructure practitioners worldwide.

Scope & limitations

High-level theoretical roofline models do not account for tail-latency jitter from asynchronous PCIe bus transfers.

Context: NVIDIA Ampere/Hopper architectures, SRAM bandwidth, Tensor Cores, roofline analysis.

View mission

Guides to evaluating AI expertise