llama.cpp
vulkan: fix flash attention dot product precision
#20589
Merged

vulkan: fix flash attention dot product precision #20589

0cc4m
0cc4m vulkan: fix flash attention dot product precision
f916fe6e
0cc4m 0cc4m requested a review from jeffbolznv jeffbolznv 19 days ago
github-actions github-actions added Vulkan
github-actions github-actions added ggml
jeffbolznv
jeffbolznv approved these changes on 2026-03-15
0cc4m 0cc4m merged 46dba9fc into master 18 days ago
0cc4m 0cc4m deleted the 0cc4m/vulkan-flash-attention-fix-glm4 branch 18 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone