facebookresearch/ToMe

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1207 stars · 88 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ToMe (Token Merging) is a PyTorch library from Meta AI that speeds up existing Vision Transformers by merging similar tokens inside the network, giving 2-3x faster evaluation with no retraining required. It provides patching tools for popular ViT implementations like timm, SWAG, and MAE.

Use cases

• speed up vision transformer inference
• reduce memory usage of ViT models
• apply token merging to timm models without retraining
• visualize how ViT tokens group image regions
• train ViTs faster with token merging
• benchmark ViT throughput improvements

When to choose

• you already use a supported ViT implementation (timm, SWAG, MAE) and want faster inference without retraining
• you need to cut ViT memory footprint on limited GPU resources
• you're researching token reduction methods for transformers

When to avoid

• you use a ViT implementation not supported by the patching tools
• you need guaranteed accuracy with zero tolerance for drops
• you need maintained production software - the repo is research code with infrequent updates

Facets

library · maturity maintenance

machine-learning deep-learning image-processing benchmarking deep-learning computer-vision machine-learning image-processing python cross-platform vision-transformer token-merging pytorch model-optimization inference-speedup timm research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/ToMe")