Comparison
gpt-neox vs Liger-Kernel
Verdict
Pick gpt-neox if gPT-NeoX from EleutherAI leverages GPU-based model parallelism via Megatron and DeepSpeed libraries to facilitate the training of large-scale autoregressive transformers in Python, under an Apache-2.0 license; pick Liger-Kernel if optimized Triton kernels for accelerating LLM training, especially on ROCm PyTorch installations.
Markdown twin · gpt-neox alternatives · Liger-Kernel alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | gpt-neox | Liger-Kernel |
|---|---|---|
| Maintenance | Steady (56d since push) As of 2w · github_public_v1 | Very active (0d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Organization 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 | No lockfile (source not queried) 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
- gpt-neox
- Implementation of model parallel autoregressive transformers on GPUs based on Megatron and DeepSpeed libraries
- Liger-Kernel
- Efficient Triton Kernels for LLM Training
Stars
- gpt-neox
- 7.5k
- Liger-Kernel
- 6.6k
Forks
- gpt-neox
- 1.1k
- Liger-Kernel
- 573
Open issues
- gpt-neox
- 111
- Liger-Kernel
- 190
Language
- gpt-neox
- Python
- Liger-Kernel
- Python
Adopt for
- gpt-neox
- GPT-NeoX from EleutherAI leverages GPU-based model parallelism via Megatron and DeepSpeed libraries to facilitate the training of large-scale autoregressive transformers in Python, under an Apache-2.0 license.
- Liger-Kernel
- Optimized Triton kernels for accelerating LLM training, especially on ROCm PyTorch installations.
Persona
- gpt-neox
- -
- Liger-Kernel
- -
Runtime
- gpt-neox
- -
- Liger-Kernel
- -
License
- gpt-neox
- The tool is licensed under Apache-2.0, allowing permissive use but emphasizing that derivative works must preserve copyright headers and licenses as per their origins
- Liger-Kernel
- BSD-2-Clause
Last pushed
- gpt-neox
- Jun 11, 2026
- Liger-Kernel
- Aug 7, 2026
Categories
- gpt-neox
- LLM Frameworks, Model Training
- Liger-Kernel
- Model Training
Trust and health
Maintenance
- gpt-neox
- Steady (60%)
- Liger-Kernel
- Very active (96%)
Days since push
- gpt-neox
- 56d
- Liger-Kernel
- 0d
Open issues (now)
- gpt-neox
- 111
- Liger-Kernel
- 190
Full report
- gpt-neox
- Trust report
- Liger-Kernel
- Trust report
Choose gpt-neox if…
- License: gpt-neox is Apache-2.0, Liger-Kernel is BSD-2-Clause.
- Pricing: Free to use with the caveat of adhering to the Apache License terms, particularly in preserving copyright and license headers for all derivations..
- Tags unique to gpt-neox: deepspeed-library, gpt-3, language-model, transformers.
- Also covers LLM Frameworks.
- - When your project requires a framework based on state-of-the-art libraries like Megatron and DeepSpeed that are optimized for large GPU clusters.
When NOT to use gpt-neox
- - In scenarios where minimal hardware resources, such as a single low-memory GPU or CPU-only environments, are available for training due to GPT-NeoX's requirement for a large-scale infrastructure.
- - If your project is limited by the Apache License terms or requires proprietary codebases without open-source contributions and modifications from external parties.
Choose Liger-Kernel if…
- License: Liger-Kernel is BSD-2-Clause, gpt-neox is Apache-2.0.
- Tags unique to Liger-Kernel: finetuning, gemma2, llama, mistral.
- When enhancing training speed of large language models with ROCm-compatible hardware.
When NOT to use Liger-Kernel
- Avoid if only CUDA environments are supported, as Liger-Kernel emphasizes ROCm compatibility.
- Skip for simple setup requirements; prefer more streamlined tools without extensive customization options.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (EleutherAI/gpt-neox) · observed Aug 7, 2026
- GitHub forks (EleutherAI/gpt-neox) · observed Aug 7, 2026
- Last push (EleutherAI/gpt-neox) · observed Jun 11, 2026
- License file (Apache-2.0) · observed Aug 7, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (linkedin/Liger-Kernel) · observed Aug 7, 2026
- GitHub forks (linkedin/Liger-Kernel) · observed Aug 7, 2026
- Last push (linkedin/Liger-Kernel) · observed Aug 7, 2026
- License file (BSD-2-Clause) · observed Aug 7, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: gpt-neox 7.5k · Liger-Kernel 6.6k (synced Aug 7, 2026).
Common questions
- What is the difference between gpt-neox and Liger-Kernel?
- gpt-neox: Implementation of model parallel autoregressive transformers on GPUs based on Megatron and DeepSpeed libraries. Liger-Kernel: Efficient Triton Kernels for LLM Training. See the comparison table for live GitHub stats and shared categories.
- When should I choose gpt-neox over Liger-Kernel?
- Choose gpt-neox over Liger-Kernel when License: gpt-neox is Apache-2.0, Liger-Kernel is BSD-2-Clause; Pricing: Free to use with the caveat of adhering to the Apache License terms, particularly in preserving copyright and license headers for all derivations.; Tags unique to gpt-neox: deepspeed-library, gpt-3, language-model, transformers; Also covers LLM Frameworks; - When your project requires a framework based on state-of-the-art libraries like Megatron and DeepSpeed that are optimized for large GPU clusters.
- When should I choose Liger-Kernel over gpt-neox?
- Choose Liger-Kernel over gpt-neox when License: Liger-Kernel is BSD-2-Clause, gpt-neox is Apache-2.0; Tags unique to Liger-Kernel: finetuning, gemma2, llama, mistral; When enhancing training speed of large language models with ROCm-compatible hardware.
- When should I avoid gpt-neox?
- - In scenarios where minimal hardware resources, such as a single low-memory GPU or CPU-only environments, are available for training due to GPT-NeoX's requirement for a large-scale infrastructure. - If your project is limited by the Apache License terms or requires proprietary codebases without open-source contributions and modifications from external parties.
- When should I avoid Liger-Kernel?
- Avoid if only CUDA environments are supported, as Liger-Kernel emphasizes ROCm compatibility. Skip for simple setup requirements; prefer more streamlined tools without extensive customization options.
- Is gpt-neox or Liger-Kernel more popular on GitHub?
- gpt-neox has more GitHub stars (7,452 vs 6,555). Stars measure visibility, not whether either tool fits your constraints.
- Are gpt-neox and Liger-Kernel open source?
- Yes - both are open-source projects on GitHub (gpt-neox: Apache-2.0, Liger-Kernel: BSD-2-Clause).
- Where can I find alternatives to gpt-neox or Liger-Kernel?
- GraphCanon lists graph-backed alternatives at gpt-neox alternatives and Liger-Kernel alternatives (gpt-neox markdown twin, Liger-Kernel 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, gpt-neox or Liger-Kernel?
- gpt-neox: Steady. Liger-Kernel: 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 gpt-neox and Liger-Kernel?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: gpt-neox trust report; Liger-Kernel trust report.