Addressed a double free bug when running on CPU introduced in the last commit as well as an issue loading SDXL LoRAs #200
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
…eg: CLIP and the primary backend, as this would result in the *_backend pointers both pointing to the same thing resulting in a segfault when calling the StableDiffusionGGML destructor.
…face. Changed the base log_printf function to not bake the log level directly into the log buffer as that information is already passed the logging function via the level parameter and it's easier to add in there than strip it out.
…cted naming convention, converts over the tensor name during the LoRA model loading. Added some logging of useful LoRA loading information. Had to increase the base size of the GGML graph as the existing size results in an insufficient graph memory error when using SDXL LoRAs.
Closed
grauho
changed the title
|
I have also encountered this issue. When using it on Windows 11, I encountered a "Segmentation fault". My fix: $ git diff
diff --git a/stable-diffusion.cpp b/stable-diffusion.cpp
index 4d622dd..1fa115e 100644
--- a/stable-diffusion.cpp
+++ b/stable-diffusion.cpp
@@ -123,9 +123,13 @@ public:
~StableDiffusionGGML() {
ggml_backend_free(backend);
- ggml_backend_free(clip_backend);
+ if (clip_backend != backend) {
+ ggml_backend_free(clip_backend);
+ }
ggml_backend_free(control_net_backend);
- ggml_backend_free(vae_backend);
+ if (vae_backend != backend) {
+ ggml_backend_free(vae_backend);
+ }
} |
|
Great! Thank you for fixing this problem. |
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Outdated suggestions cannot be applied.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.
Fixed a double free issue when running multiple backends on the CPU, eg: CLIP and the primary backend, as this would result in the *_backend pointers both pointing to the same thing resulting in a segfault when calling the StableDiffusionGGML destructor.