LlamaIndex
Log in

Find answers from the community

Updated 2 months ago

When using `HuggingFaceEmbeddings` to

GGpt. Alex
·
When using HuggingFaceEmbeddings to generate embeddings, how do I specify that I want the GPU to be used? Is there something like langchains model_kwargs?
L
G
3 comments
LLogan M
It uses GPU by default if cuda is available
LLogan M
Optionally you can specify the device device="cuda:0"
GGpt. Alex
perfect, thanks!
Add a reply
Sign up and join the conversation on Discord