fix: further increase LORA_GRAPH_SIZE #717
Closed
Conversation
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
It turns out 15360 is still not enough for some SDXL LoRAs; for instance, a quantized SDXL model with the DMD2 LoRA. Koboldcpp has been using 20480 for some time, so this value should be enough. Hopefully fixes leejet#648 , leejet#684 and leejet#688 .
|
Could you give an example of a LoRA? |
|
I was able to reproduce it with the DMD2 acceleration LoRA (https://huggingface.co/tianweiy/DMD2/blob/main/dmd2_sdxl_4step_lora_fp16.safetensors), but only with a quantized model (Q5_0 or Q8_0); all fp16 models I've tried worked fine with 15360 as the limit. |
|
I think it would be better to make the lora graph variable. In the latest master commit, I made the corresponding change. |
|
Did a few tests with 1ce1c1a ; the resulting size was a bit of an overkill for the dmd2 LoRA (33880), but it worked fine. Thanks! |
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Outdated suggestions cannot be applied.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.
It turns out 15360 is still not enough for some SDXL LoRAs; for instance, a quantized SDXL model with the DMD2 LoRA.
Koboldcpp has been using 20480 for some time, so this value should be enough.
Hopefully fixes #648 , #684 and #688 .