Skip to content

Conversation

@jeffbolznv
Copy link
Collaborator

Fixes #15678.

This inadvertently disabled robustness, which could lead to OOB accesses in the shader.

@jeffbolznv jeffbolznv requested a review from 0cc4m as a code owner September 1, 2025 15:28
Copy link
Collaborator

@0cc4m 0cc4m left a comment

Choose a reason for hiding this comment

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

I messed up the order, damn. That was so easy to miss.

@github-actions github-actions bot added Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning labels Sep 1, 2025
@taronaeo taronaeo merged commit 25f1045 into ggml-org:master Sep 2, 2025
48 checks passed
walidbr pushed a commit to walidbr/llama.cpp that referenced this pull request Sep 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Misc. bug: Build 6278 Vulkan crashes: llama-bench and llama-server both affected

3 participants