Source: https://seerepo.com/compare/ace-step/ACE-Step-1.5/vs/hiyouga/LlamaFactory
Markdown source: https://seerepo.com/compare/ace-step/ACE-Step-1.5/vs/hiyouga/LlamaFactory.md
Description: ACE-Step-1.5 and LlamaFactory share 16 technologies: FastAPI, uvicorn, Gradio, matplotlib, accelerate, torchvision, torch, transformers, einops, vector-quantize-pytorch, peft, safetensors, torchaudio, torchao, ModelScope, and torchcodec. Both are written in Python.

# ACE-Step-1.5 vs LlamaFactory

ACE-Step-1.5 and LlamaFactory share 16 technologies: FastAPI, uvicorn, Gradio, matplotlib, accelerate, torchvision, torch, transformers, einops, vector-quantize-pytorch, peft, safetensors, torchaudio, torchao, ModelScope, and torchcodec. Both are written in Python.

- [ace-step/ACE-Step-1.5](https://seerepo.com/r/ace-step/ACE-Step-1.5): The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
- [hiyouga/LlamaFactory](https://seerepo.com/r/hiyouga/LlamaFactory): Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

## What they share and what sets them apart

- In common: FastAPI, uvicorn, Gradio, matplotlib, accelerate, torchvision, torch, transformers, einops, vector-quantize-pytorch, peft, safetensors, torchaudio, torchao, ModelScope, torchcodec
- Only in ACE-Step-1.5: diskcache, Lightning, Textual, Rich, triton-windows, mlx, flash-attn, triton, diffusers, mlx-lm, loguru
- Only in LlamaFactory: aqlm, eetq, gptqmodel, hqq, ktransformers, sentencepiece, tiktoken, triton-ascend, vocos, datasets, trl, badam, deepspeed, torch-npu, vLLM, fsdp-turbo, liger-kernel, openmind, adam-mini, apollo-torch, bitsandbytes, galore-torch, nltk, optimum, rouge-chinese, sglang, torchdata, transformer-engine, av, jsonschema-specifications, referencing, Pydantic, swanlab

## Side by side

| | ACE-Step-1.5 | LlamaFactory |
|---|---|---|
| Size | 126,537 lines written, 410 code files | 62,648 lines written, 194 code files |
| Who writes it | 35.8% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, Codex, Jules, and CodeRabbit | 1.6% of its commits signed by AI. With Gemini CLI, Claude Code, GitHub Copilot, and Cursor |
| Activity | Last push November 8, 2026, 1,104 commits, 14,532 stars | Last push November 9, 2026, 2,772 commits, 75,956 stars |
| Tests | 190 test files. 46.8% of its code files have a test that imports them | 62 test files. 38.1% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, ACE-Step-1.5 or LlamaFactory?

ACE-Step-1.5, with 126,537 lines written; LlamaFactory has 62,648.

The proof: [ace-step/ACE-Step-1.5's code at commit ca1e85f](https://github.com/ace-step/ACE-Step-1.5/tree/ca1e85fe9430179831e6bc6be790c332190a3866)

### Which has more GitHub stars, ACE-Step-1.5 or LlamaFactory?

LlamaFactory, with 75,956 stars; ACE-Step-1.5 has 14,532.

The proof: [hiyouga/LlamaFactory on GitHub](https://github.com/hiyouga/LlamaFactory)

### Which has more tests, ACE-Step-1.5 or LlamaFactory?

ACE-Step-1.5, with 190 test files; LlamaFactory has 62.

The proof: [ace-step/ACE-Step-1.5's code at commit ca1e85f](https://github.com/ace-step/ACE-Step-1.5/tree/ca1e85fe9430179831e6bc6be790c332190a3866)

### Which was updated more recently, ACE-Step-1.5 or LlamaFactory?

LlamaFactory: its last push was on November 9, 2026, and ACE-Step-1.5's on November 8, 2026.

The proof: [hiyouga/LlamaFactory's commits on GitHub](https://github.com/hiyouga/LlamaFactory/commits)

### Which has more commits signed by AI, ACE-Step-1.5 or LlamaFactory?

ACE-Step-1.5: an AI signed 35.8% of its commits, with Claude Code, GitHub Copilot, Cursor, Codex, Jules, and CodeRabbit; in LlamaFactory, 1.6%.

The proof: [the commits each tool signed in ace-step/ACE-Step-1.5](https://seerepo.com/r/ace-step/ACE-Step-1.5/ai)

## Sources

- ace-step/ACE-Step-1.5: Read on November 9, 2026, at commit ca1e85f (https://github.com/ace-step/ACE-Step-1.5/tree/ca1e85fe9430179831e6bc6be790c332190a3866)
- hiyouga/LlamaFactory: Read on November 9, 2026, at commit 28462f1 (https://github.com/hiyouga/LlamaFactory/tree/28462f15cc00b8233afab64c7712650d0a18a273)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.