Inductor

Triton is a kernel language that PyTorch Inductor commonly generates for GPU targets. In the torch.compile pipeline, it is part of the stage that generates optimized code for PyTorch models.

DeepJIT is a lightweight, header-only C++20 library for just-in-time compilation, caching, loading, and launching of device kernels on NVIDIA CUDA GPUs and Huawei Ascend NPUs. It provides a shared runtime interface for both backends while keeping kernel source and compiler options backend-specific. The runtime hashes kernel source, tracked includes, compiler information, effective options, and application-provided dependency signatures to reuse compiled artifacts through in-memory and on-disk caches. Cache directories can be shared across users, processes, and nodes on local or distributed filesystems, with completed entries published through atomic directory renames. Lazy initialization defers device and compiler discovery until first use. DeepJIT integrates with PyTorch CUDA and torch_npu streams and can expose a runtime through pybind11. The CUDA backend uses NVCC and the CUDA Driver API to produce, load, and launch CUBIN files; the Ascend backend uses Bisheng, ld.lld, and ACL to compile, link, load, and launch kernels. It supports per-kernel compiler and launch options, compilation diagnostics, and optional PTX, SASS, or Ascend assembly dumps. The host environment requires Linux, a C++20 compiler with std::format support, Python, pybind11, and the dependencies for the selected backend; it is intended to be embedded in another C++ or Python extension as a header-only dependency.

torch.compile is PyTorch's model compilation tool. It inspects a model before execution and converts as much of its computation as possible into an optimized region, allowing compiler transformations such as kernel fusion, operation reordering, and memory planning. Python scalar reads such as `.item()` can cause graph breaks that fragment these regions and force synchronization between Python and the accelerator, reducing available optimization and potentially slowing execution.

AOT Autograd is a PyTorch compilation component used as the second stage of torch.compile. It prepares a captured graph for a backend by decomposing high-level operations and capturing the backward graphs needed for training.

CUDA is a parallel computing platform and programming model developed by NVIDIA that enables general-purpose computing on NVIDIA GPUs. It includes the CUDA Toolkit (compilers, libraries, and developer tools) and APIs for C, C++ and Fortran to accelerate compute-intensive applications in areas such as scientific computing, HPC, graphics, and machine learning.