Support full-precision embeddings in half precision inference mode - #110
Merged
Conversation
Collaborator
|
Interesting. Does it still work with the same memory footprint as the half precision implementation? |
Contributor
Author
Yes, I use this to run inference with custom embeddings on an 8GB GPU, because it is not enough VRAM for full-precision. Without this pr implemented, I cannot use custom embeddings, I get an error about a mismatch between half and full precision. |
Contributor
|
lg2m. thanks for the fix! |
Collaborator
|
I'm very grateful for this @sajattack. I'll do a round of testing tomorrow morning. @Oceanswave , could you review as well? (this is an edit- assigned did not mean to assign @blessedcoolant ) |
|
Thanks @sajattack for this PR. Now embeddings.pt finally works on my 8GB VRAM GPU! |
austinbrown34
pushed a commit
to cognidesign/InvokeAI
that referenced
this pull request
Dec 30, 2022
…ings Support full-precision embeddings in half precision inference mode
lstein
added a commit
that referenced
this pull request
Mar 8, 2026
* Add user management UI for admin and regular users (#106) * Add user management UI and backend API endpoints Co-authored-by: lstein <111189+lstein@users.noreply.github.com> Fix user management feedback: cancel/back navigation, system user filter, tooltip fix Co-authored-by: lstein <111189+lstein@users.noreply.github.com> Make Back button on User Management page more prominent Co-authored-by: lstein <111189+lstein@users.noreply.github.com> * chore(frontend): typegen --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: lstein <111189+lstein@users.noreply.github.com> Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> * Add Confirm Password field to My Profile password change form (#110) Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: lstein <111189+lstein@users.noreply.github.com> --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: lstein <111189+lstein@users.noreply.github.com> Co-authored-by: Alexander Eichhorn <alex@eichhorn.dev>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Cast embeddings down to the correct precision