Exllamav2 lora support #4229
Merged
Exllamav2 lora support #4229
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
|
Its working for 70b now. |
|
Nice. I'm waiting for a 0.0.6 release to merge this. |
Unload lora so the memory is freed at next generation. Otherwise swapping many LoRA would cause OOM.
|
It should be working for multiple LoRAs now (if you find any issue, please let me know) |
Mistral + Lora works with exllamav2. This fixes #4272 Thank you! |
1 task
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Outdated suggestions cannot be applied.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.
Doesn't work for multi GPU because of a kernel bug but it does work on single card models. Tested it for llama 7b.
Somehow multiple loras are possible but I'm not sure how to make that work.