Skip to content

[Debug] Update GLM-Image Pipeline #1049

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
david6666666 merged 2 commits into from
Jan 29, 2026
+2 −2
Merged

[Debug] Update GLM-Image Pipeline #1049

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f446d40
debug: glm image
Jan 29, 2026
814ce4a
Refactor: Simplify condition image processing in GlmImagePipeline
Jan 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm_omni/diffusion/models/glm_image/pipeline_glm_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,7 +491,7 @@ def generate_prior_tokens(
condition_grid = image_grid_thw[:-1]
prior_token_image_embed = self.vision_language_encoder.get_image_features(
inputs["pixel_values"], condition_grid
)
).pooler_output
prior_token_image_embed = torch.cat(prior_token_image_embed, dim=0)
Comment on lines 491 to 495
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot Jan 29, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Remove torch.cat on pooled image features tensor

With the new .pooler_output access, prior_token_image_embed is a single tensor (the pooled image features). torch.cat(prior_token_image_embed, dim=0) now raises TypeError: cat() received an invalid combination of arguments because torch.cat requires a sequence of tensors, not a tensor. This will crash image-edit requests that include condition images (the only path where this block runs). Consider using the tensor directly (or wrapping it in a list only if you truly need to concatenate multiple tensors).

Useful? React with 👍 / 👎.

flat_prior_token_image_ids = self.vision_language_encoder.get_image_tokens(
prior_token_image_embed, condition_grid
Expand Down Expand Up @@ -859,7 +859,7 @@ def forward(self, req: OmniDiffusionRequest) -> DiffusionOutput:
preprocessed_images = (
None
if isinstance(first_prompt, str)
else first_prompt.get("additional_information", {}).get("preprocessed_image")
else [first_prompt.get("additional_information", {}).get("preprocessed_image")]
)
condition_images = (
None
Expand Down