# tensorflow/mlir

"Multi-Level Intermediate Representation" Compiler Infrastructure

Repository: https://github.com/tensorflow/mlir
Canonical: https://ross.abutalabs.com/products/mlir
License Family: other
Archived: true
Last push: 2021-04-22T22:24:29+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2714, "days_push": 1959, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1768, forks 259 (observed 2026-08-28T04:05:33.700873+00:00)

## What it is
MLIR (Multi-Level Intermediate Representation) is a compiler infrastructure for building reusable and extensible compiler toolchains, originally developed under TensorFlow. This repository has been migrated into the LLVM monorepo and now redirects there.

## Use cases
- build custom compiler toolchains with a flexible IR
- compile and optimize machine learning models
- design domain-specific intermediate representations
- lower ML graphs to hardware targets

## When to choose
- you need a multi-level IR for building compilers or ML compilers
- you want to contribute to or use MLIR today - use the LLVM monorepo version

## When to avoid
- you expect active development in this repository - it is archived and moved to llvm/llvm-project
- you need a stable release - no releases were published from this repo

## Facets
- artifact type: framework
- maturity: abandoned
- function: compiler, interpreter, developer-tools
- domain: compilers, machine-learning, developer-tools
- platform: cpp, windows
- tags: intermediate-representation, compiler-infrastructure, llvm, moved-to-llvm, linux, macos

## Member repositories
- tensorflow/mlir (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:33.700873+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 2026-08-30T03:26:23.514611+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/mlir (fetched 2026-08-28T04:05:33.700873+00:00, sha b5517ae9ea93)
- Data as of 2026-08-30T08:39:29.467469+00:00.