agentleFS
onnxonnx/onnx-mlir/.agents/skills/onnx-mlir-internals/SKILL.md

onnx-mlir-internals

Skill1.1k starsChanged 12 days agoApache-2.0View on GitHub

Background on onnx-mlir compiler internals: IndexExpr and shape helpers, the dialect builders (create.krnl, create.onnx, ...), ONNX-to-Krnl and Krnl-to-Affine lowering mechanics, loop collapse and parallel planning, recompose and ONNXFusedOp fusion, and which -march/flags change codegen. Use when you need to understand how these pieces work, not just follow a recipe.

Trending

Quiet since December.about the whole repository

Dec 2025: 1 mentionJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the onnx/onnx-mlir repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about onnx/onnx-mlir

The biggest 5 of 22 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 22

Talked about on GitHub (22 times).

On GitHub · 22

17 more on GitHub

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only the reference you need:

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from the onnx-mlir knowledge base (generated briefing), verified against onnx-mlir@b505d64b. Do not edit here: see .agents/skills/README.md. -->

onnx-mlir Internals

Reference material that the task skills in this directory link to. Each file explains one part of the compiler; the task skills (add-onnx-op-lowering, add-new-onnx-operation, add-fusion-pattern, ground-lit-tests, ...) say when to read which.

Read only the reference you need:

  • Dialect Builders: onnx-mlir provides a set of builder structs that wrap MLIR's OpBuilder with type-dispatched, location-implicit APIs for each dialect used during lowering.
  • IndexExpr: IndexExpr is a unified data structure for index computations that works identically during shape inference (no code generation, compile-time only) and lowering (code generation into MLIR IR).
  • Interface: Krnl Dialect → Affine/SCF Dialects: The KrnlToAffine pass lowers Krnl loop constructs to MLIR's Affine and SCF dialects, applying the blocking and permutation annotations specified during ONNXToKrnl lowering.
  • Interface: ONNX Dialect → Krnl Dialect (selected sections): The ConvertONNXToKrnlPass lowers each ONNX op into Krnl loop constructs plus Affine/MemRef/Arith/Math ops.
  • onnx-mlir Compiler (selected sections): The compiler module (src/Compiler/) implements the compilation driver, option parsing, and pass pipeline construction.
  • ONNX Dialect (selected sections): The ONNX dialect (src/Dialect/ONNX/) is the primary representation of the neural network graph within onnx-mlir.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.