GraphCanon updated 3w · GitHub synced 3w
Decision brief
FastEdit is a Python library for quick edits to large language models using PyTorch.
Good fit when
- When rapid iterations on language model edits are necessary, such as testing and tuning with tight feedback loops.
- If you aim to work specifically within the FP16 precision mode requiring 24GB RAM for a 7B LLaMA model or 32GB RAM for a 13B version.
Avoid when
- If your workflow requires integration with TensorFlow instead of PyTorch, since FastEdit is built on top of PyTorch.
- For hardware configurations that cannot meet the fast editing mode's requirements; for instance, if you have less than 24GB RAM available.
- Requirements:
- Min -1 GB RAM; Requires Python 3.8+ and PyTorch 1.13.1+. Must also install 🤗Transformers, Datasets, Accelerate, sentencepiece, and fire.; Hardware requirements for a specific model can vary; refer to the provided table for minimum RAM sizes for different models.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1086d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 73 low (73 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install FastEditSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
FastEdit is a Python library designed for efficient editing of large language models, such as LLaMA and others, using PyTorch.
Capability facts
- Languages
- python
Source: github.language+pyproject.toml · Aug 3, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 3, 2026)
- Python 3.8+ and PyTorch 1.13.1+Source link
Tags
README
Requirements
- Python 3.8+ and PyTorch 1.13.1+
- 🤗Transformers, Datasets and Accelerate
- sentencepiece and fire
Hardware Requirements
| Model | Size | Mode | GRAM | Speed |
|---|---|---|---|---|
| LLaMA | 7B | FP16 | 24GB | 7s/it |
| LLaMA | 13B | FP16 | 32GB | 9s/it |
Installation
git clone https://github.com/hiyouga/FastEdit.git
conda create -n fastedit python=3.10
conda activate fastedit
cd FastEdit
pip install -r requirements.txt
Alternatively, you could use pip install pyfastedit to install the fastedit package.
License
This repository is licensed under the Apache-2.0 License.
For agents
This page has a .md twin and JSON over the API.