Results for "elastic compute"

Increasing model capacity via compute.

Regulating access to large-scale compute.

Number of samples per gradient update; impacts compute efficiency, generalization, and stability.

Letting an LLM call external functions/APIs to fetch data, compute, or take actions, improving reliability.

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Empirical laws linking model size, data, compute to performance.

Scaling law optimizing compute vs data.

Storing results to reduce compute.

Stored compute or algorithms enabling rapid jumps.

Hardware resources used for training/inference; constrained by memory bandwidth, FLOPs, and parallelism.