Try transformers experimental streaming. Still uses threads, so probably won't fix browser exit GPU memory issue #98
Conversation
This file contains 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
…bly won't fix browser exit GPU memory issue
… kills/clears old thread if another generate comes along
|
High concurrency (10) runs fine (just slower), no more memory.
and hit this: this breaks a given user. But maybe that's ok, but seems should be recoverable even for that user. |
…input, including nochat, with accounting of inputs used (nochat uses text box for instruction/iinput, while chat uses history).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
One this is fixed: gradio-app/gradio#4016 then can incorporate that and rely upon stopping to clear activate generate instead of just waiting for those threads to finish.