Open Models Almanac
Methodsoptimization

specific method · filed under optimization

Gradient checkpointing

Uses gradient checkpointing during training, including through a configuration flag, as a scaling lever.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See optimization for the methods filed beside it.

Also called gradient_checkpointing=true.

sources
2
models
2
labs adopt it
2
strongest
used

Documented in

Toyota Research Institute
Hugging Face

Evidence

3 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
optional 1used 1unclear 1

VLA Foundry (Foundry-VLA-1.7B)

Toyota Research Instituteadopted1 source

The training loop supports the standard levers for scaling distributed training – FSDP (with optional CPU offloading), mixed precision, gradient checkpointing, torch.compile, and gradient accumulation.

usedoptimizationin VLA FoundryToyota Research Institute
1 more from this model

gradient accumulation, gradient checkpointing, torch.compile

unclearoptimizationin VLA FoundryToyota Research Institute
↑