# Triton and compiler-generated kernels

> How Triton's block-level model and autotuning work, what TorchInductor generates automatically, and where Triton gives less control.

- Web page: https://www.alesanalytics.com/docs/triton-and-compiler-generated-kernels
- Markdown: https://www.alesanalytics.com/docs/triton-and-compiler-generated-kernels.md
- Last updated: 2026-11-08
- Publisher: Ales Analytics

Technical page. Block-level kernels and torch.compile. Published 2026-11-08. Last reviewed 2026-11-08. Reviewed by Ales Analytics engineering.

## In one paragraph

Triton is a Python-embedded language for writing GPU kernels at the level of blocks of data rather than individual threads. The compiler takes care of much of what makes CUDA hard: coalescing, staging data through shared memory, and scheduling. PyTorch's `torch.compile` generates Triton kernels automatically through TorchInductor, which covers most fusion opportunities without anyone writing a kernel.

## How it works

- **Programs and blocks.** Each program instance works on a block of data, identified by `tl.program_id`. Loads and stores take masks for blocks that run past the end of the data.
- **Autotuning.** `triton.autotune` tries configurations such as block sizes, warp counts and pipeline stages, and caches the fastest per input shape.
- **TorchInductor.** The default `torch.compile` backend fuses elementwise and reduction operations into generated Triton kernels.
- **Helion.** A higher-level PyTorch kernel language that compiles to Triton, currently in beta.

## Design choices and trade-offs

- **Triton vs CUDA.** Triton is far quicker to write and port across NVIDIA generations; exact warp specialisation, register control and some of the newest hardware features are easier from CUDA, CUTLASS or the CuTe DSL.
- **Compiler first.** Before writing a kernel, check what `torch.compile` already produces.

## When not to use it

When the operation is already a single library call (a large GEMM in cuBLAS), Triton rarely beats it.

## How we evaluate it

Against the library or compiler baseline, on the shapes the model actually uses, with correctness checked against a higher-precision reference.

## Sources

- [Triton programming guide](https://triton-lang.org/main/programming-guide/chapter-1/introduction.html)
- [Helion](https://pytorch.org/blog/helion/)
- [GPU kernel engineering](https://www.alesanalytics.com/engineering/gpu-kernels), which includes a fused softmax in Triton

## Contact

solutions@alesanalytics.com, or https://www.alesanalytics.com/contact.

- Every page as Markdown: https://www.alesanalytics.com/llms.txt