facebookresearch/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #275 of 2,794 repositories GStars tracks this week (top 10%).
No releases in the last 90 days; the most recent was 243 days ago, with 111 contributors on GitHub.
Gained 61% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides customizable and optimized Transformer building blocks for efficient and flexible model construction.
- Delivers memory-efficient and fast Transformer components with custom CUDA kernels, enabling faster iteration than standard libraries.
- Use for developing cutting-edge NLP models requiring exact and memory-efficient attention mechanisms.
- Use for building vision Transformer architectures that benefit from sparse and block-sparse attention optimizations.
- Use for research projects needing modular Transformer components that integrate easily with PyTorch and support experimental features.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
Setup: A100 on f16, measured total time for a forward+backward pass
Note that this is exact attention, not an approximation, just by calling
xformers.ops.memory_efficient_attentionxFormers provides many components, and more benchmarks are available in BENCHMARKS.md.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
796+17
Open issues
374-3
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/claude-plugins-official | 43.9K | +5.6K | 35 | — |
| NationalSecurityAgency/ghidra | 93.2K | +4.9K | 75 | today |
| K-Dense-AI/scientific-agent-skills | 53.9K | +4.0K | 75 | 21 days ago |
| akitaonrails/ai-memory | 12.8K | +3.3K | 40 | today |
| shiyu-coder/Kronos | 43.2K | +2.4K | 75 | — |
| facebookresearch/xformers | 10.6K | +0 | 75 | 243 days ago |
| Category median | 43.9K | +4.0K | 75 | — |
Also by facebookresearch
Other repositories from this maintainer that GStars tracks
- Python34.9K stars
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
- Python14.5K stars
vggt
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
- Python12.1K stars
sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
- Jupyter Notebook11.6K stars
dinov3
Reference PyTorch implementation and models for DINOv3
- Python4.8K stars
vjepa2
PyTorch code and models for VJEPA2 self-supervised learning from video.
Discover Repositories
Search across tracked repositories by name or description