Skip to content

fix: fail on AttentionSlidingWindowPattern is zero #10

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

Jump to bottom
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: fail on AttentionSlidingWindowPattern is zero #10

wants to merge 1 commit into from
+2 −2

Conversation

chenyunxing
Copy link

issue address: gpustack/gpustack#2270
When AttentionSlidingWindowPattern is zero, skip checking SWA layer pattern since this value indicates all layers use Sliding Window Attention.

@chenyunxing
fix: fail on AttentionSlidingWindowPattern is zero when AttentionSlid…
801ecbf 
…ingWindowPattern is zero

When AttentionSlidingWindowPattern is zero, skip checking SWA layer pattern since this value indicates all layers use Sliding Window Attention.
@chenyunxing chenyunxing requested a review from thxCode June 27, 2025 02:43
@thxCode
Copy link
Collaborator

thxCode commented Jun 27, 2025

the issue includes two potential problems:

  1. the first is to address the division by zero error.
  2. the second is that the given model is an image-generation model: https://www.modelscope.cn/models/AI-ModelScope/FLUX.1-dev-gguf/files, it should not be recognized to run EstimateLLaMACppRun.
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@thxCode thxCode Awaiting requested review from thxCode

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@chenyunxing @thxCode