Skip to content

support gguf format for qwen3_vl_encoder - #9578

Open
grunblatt-git wants to merge 2 commits into
invoke-ai:mainfrom
grunblatt-git:qwen3-vl-gguf-support
Open

support gguf format for qwen3_vl_encoder#9578
grunblatt-git wants to merge 2 commits into
invoke-ai:mainfrom
grunblatt-git:qwen3-vl-gguf-support

Conversation

@grunblatt-git

Copy link
Copy Markdown

This PR was heavily supported by AI.

Since this new Loader allows me to load Qwen3 VL GGUF files (~2.5 GB) instead of the default 9GB textencoder files (and thus allows me to keep both textencoder and unet in VRAM without swapping), i thought i would share it.

Please review especially the key- and weight- mappings in Qwen3VLEncoderGGUFLoader. I can verify that this code works on Mac, but to me it still looks overly complex and i don't know if there exist dependencies or helper methods in Invoke that would simplify this code a lot.

@github-actions github-actions Bot added python PRs that change python files invocations PRs that change invocations backend PRs that change backend files labels Sep 8, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

backend PRs that change backend files invocations PRs that change invocations python PRs that change python files

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant