Comparison
awesome-tensor-compilers vs onnx-mlir
Verdict
Pick awesome-tensor-compilers if decision-critical Facts for awesome-tensor-compilers; pick onnx-mlir if oNNX-MLIR is optimised for compiling ONNX models to MLIR and LLVM bytecodes, offering cross-platform support and multiple runtime environments.
Markdown twin · awesome-tensor-compilers alternatives · onnx-mlir alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | awesome-tensor-compilers | onnx-mlir |
|---|---|---|
| Maintenance | Dormant (654d since push) As of 2w · github_public_v1 | Very active (3d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Personal account As of 2w · github_public_v1 | Not a fork · Organization account As of 2w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | Published findings As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- awesome-tensor-compilers
- A collection of compiler projects and papers for tensor computation and deep learning.
- onnx-mlir
- ONNX model compiler technology lowering ONNX graphs to MLIR and LLVM bytecodes
Stars
- awesome-tensor-compilers
- 2.8k
- onnx-mlir
- 1.0k
Forks
- awesome-tensor-compilers
- 327
- onnx-mlir
- 447
Open issues
- awesome-tensor-compilers
- 4
- onnx-mlir
- 352
Language
- awesome-tensor-compilers
- -
- onnx-mlir
- C++
Adopt for
- awesome-tensor-compilers
- Decision-critical Facts for awesome-tensor-compilers
- onnx-mlir
- ONNX-MLIR is optimised for compiling ONNX models to MLIR and LLVM bytecodes, offering cross-platform support and multiple runtime environments.
Persona
- awesome-tensor-compilers
- -
- onnx-mlir
- -
Runtime
- awesome-tensor-compilers
- -
- onnx-mlir
- -
License
- awesome-tensor-compilers
- -
- onnx-mlir
- Available under the Apache License Version 2.0 (Apache-2.0). Permissions granted for reproduction, distribution, etc., as per license terms.
Last pushed
- awesome-tensor-compilers
- Oct 19, 2024
- onnx-mlir
- Jul 31, 2026
Categories
- awesome-tensor-compilers
- Inference & Serving, Model Training
- onnx-mlir
- Inference & Serving, Model Training
Trust and health
Maintenance
- awesome-tensor-compilers
- Dormant (18%)
- onnx-mlir
- Very active (96%)
Days since push
- awesome-tensor-compilers
- 654d
- onnx-mlir
- 3d
Open issues (now)
- awesome-tensor-compilers
- 4
- onnx-mlir
- 352
Owner type
- awesome-tensor-compilers
- User
- onnx-mlir
- Organization
OSV dependency advisories
- awesome-tensor-compilers
- No lockfile (source not queried)
- onnx-mlir
- Published findings
Full report
- awesome-tensor-compilers
- Trust report
- onnx-mlir
- Trust report
Choose awesome-tensor-compilers if…
- Tags unique to awesome-tensor-compilers: code generation, deep-learning, high-performance-computing, machine-learning.
- If you need references to papers on cost models and automated optimizations for tensor computation.
- More GitHub stars (2.8k vs 1.0k) - visibility, not fit.
When NOT to use awesome-tensor-compilers
- Avoid if focused solely on implementation without the need for theoretical background or detailed optimization methods.
- Not suitable if your project requires immediate integration of a specific tensor compiler technology rather than review of existing research.
Choose onnx-mlir if…
- Tags unique to onnx-mlir: llvm, mlir, onnx, runtime environments.
- For users needing compile-time optimization of ONNX models to improve inference performance in a variety of language runtimes such as C++, Java, and Python
- More recently updated (last pushed Jul 31, 2026).
When NOT to use onnx-mlir
- When quick setup and environment management are desired without using prebuilt containers, as setting up prerequisites manually may be challenging
- For teams primarily focused on real-time inference serving with dedicated AI hardware that requires specialized frameworks not covered by ONNX-MLIR's support matrix
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (merrymercy/awesome-tensor-compilers) · observed Aug 4, 2026
- GitHub forks (merrymercy/awesome-tensor-compilers) · observed Aug 4, 2026
- Last push (merrymercy/awesome-tensor-compilers) · observed Oct 19, 2024
- License file (unknown) · observed Aug 4, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (onnx/onnx-mlir) · observed Aug 4, 2026
- GitHub forks (onnx/onnx-mlir) · observed Aug 4, 2026
- Last push (onnx/onnx-mlir) · observed Jul 31, 2026
- License file (Apache-2.0) · observed Aug 4, 2026
- Decision facts (enrichment) · observed Jul 16, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: awesome-tensor-compilers 2.8k · onnx-mlir 1.0k (synced Aug 4, 2026).
Common questions
- What is the difference between awesome-tensor-compilers and onnx-mlir?
- awesome-tensor-compilers: A collection of compiler projects and papers for tensor computation and deep learning.. onnx-mlir: ONNX model compiler technology lowering ONNX graphs to MLIR and LLVM bytecodes. See the comparison table for live GitHub stats and shared categories.
- When should I choose awesome-tensor-compilers over onnx-mlir?
- Choose awesome-tensor-compilers over onnx-mlir when Tags unique to awesome-tensor-compilers: code generation, deep-learning, high-performance-computing, machine-learning; If you need references to papers on cost models and automated optimizations for tensor computation; More GitHub stars (2.8k vs 1.0k) - visibility, not fit.
- When should I choose onnx-mlir over awesome-tensor-compilers?
- Choose onnx-mlir over awesome-tensor-compilers when Tags unique to onnx-mlir: llvm, mlir, onnx, runtime environments; For users needing compile-time optimization of ONNX models to improve inference performance in a variety of language runtimes such as C++, Java, and Python; More recently updated (last pushed Jul 31, 2026).
- When should I avoid awesome-tensor-compilers?
- Avoid if focused solely on implementation without the need for theoretical background or detailed optimization methods. Not suitable if your project requires immediate integration of a specific tensor compiler technology rather than review of existing research.
- When should I avoid onnx-mlir?
- When quick setup and environment management are desired without using prebuilt containers, as setting up prerequisites manually may be challenging For teams primarily focused on real-time inference serving with dedicated AI hardware that requires specialized frameworks not covered by ONNX-MLIR's support matrix
- Is awesome-tensor-compilers or onnx-mlir more popular on GitHub?
- awesome-tensor-compilers has more GitHub stars (2,770 vs 1,039). Stars measure visibility, not whether either tool fits your constraints.
- Are awesome-tensor-compilers and onnx-mlir open source?
- Yes - both are open-source projects on GitHub.
- Where can I find alternatives to awesome-tensor-compilers or onnx-mlir?
- GraphCanon lists graph-backed alternatives at awesome-tensor-compilers alternatives and onnx-mlir alternatives (awesome-tensor-compilers markdown twin, onnx-mlir markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, awesome-tensor-compilers or onnx-mlir?
- awesome-tensor-compilers: Dormant. onnx-mlir: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for awesome-tensor-compilers and onnx-mlir?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: awesome-tensor-compilers trust report; onnx-mlir trust report.