Improvement of query response time with GPU #306
Labels
enhancement
New feature or request
primordial
Related to the primordial version of PrivateGPT, which is now frozen in favour of the new PrivateGPT
Post ingestion, the response time to queries is very slow as it defaults to CPU. If a GPU is present, shouldn't same automatically use the GPU?
The text was updated successfully, but these errors were encountered: