New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Speed up loading blocks using safetensors #347

Closed

borzunov opened this issue Jul 13, 2023 · 1 comment

Collaborator

borzunov commented Jul 13, 2023

https://github.com/huggingface/safetensors provides a way to load tensors from a file to a GPU faster
Also, it allows to get a large shard and read from disk only a part of it to get a specific tensor (e.g., if a shard includes multiple blocks)

Collaborator Author

borzunov commented Sep 27, 2023

Done in #473.

borzunov closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment