# triton-lang/triton

Development repository for the Triton language and compiler

Repository: https://github.com/triton-lang/triton
Canonical: https://ross.abutalabs.com/products/triton
Homepage: https://triton-lang.org/
Language: MLIR
License: MIT
License Family: permissive
Last push: 2026-08-27T00:04:56+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 77, longevity 100
- inputs: {"age_days": 4386, "days_push": 7, "days_rel": 76, "gap_med": 70, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 20017, forks 3141 (observed 2026-08-28T04:11:29.540203+00:00)

## What it is
Triton is an open-source language and compiler for writing highly efficient custom deep-learning GPU kernels with Python-level productivity. It compiles tiled neural network computations via LLVM/MLIR, offering more flexibility than typical DSLs and higher productivity than raw CUDA.

## Use cases
- write custom GPU kernels for deep learning
- implement fused attention or matmul kernels without CUDA
- optimize neural network primitives for NVIDIA GPUs
- prototype high-performance ML kernels in Python
- compile tiled tensor computations to GPU code

## When to choose
- you need custom GPU kernels beyond what PyTorch ops provide
- you want CUDA-level performance with Python-level productivity
- you are building a compiler or runtime that generates GPU code
- you need portable kernel code across GPU architectures

## When to avoid
- you only need standard neural network layers already covered by PyTorch or JAX
- you target CPUs exclusively without GPU hardware
- you need fine-grained low-level control over warp scheduling that CUDA exposes
- you want a stable, frozen API for production embedding without tracking upstream changes

## Facets
- artifact type: library
- maturity: active
- function: compiler, programming-language, gpu-computing, machine-learning, deep-learning
- domain: compilers, gpu-computing, machine-learning, deep-learning, programming-languages
- platform: python, cpp
- tags: dsl, cuda-alternative, kernel-authoring, mlir, llvm, compiler-infrastructure, linux, gpu

## Member repositories
- triton-lang/triton (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:29.540203+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:59:22.742734+00:00, confidence not recorded.
  - readme: https://github.com/triton-lang/triton (fetched 2026-08-28T04:11:29.540203+00:00, sha 6315a1512042)
  - homepage: https://triton-lang.org/ (fetched 2026-08-29T07:57:50.778204+00:00, sha 5b0388506b7b)
- Data as of 2026-08-30T08:39:29.467469+00:00.