llama.cpp
vulkan: Use fewer rows for scalar FA when HS is not a multiple of 16
#17455
Merged

vulkan: Use fewer rows for scalar FA when HS is not a multiple of 16 #17455

0cc4m merged 2 commits into ggml-org:master from jeffbolznv:scalar_fa_hs72
jeffbolznv
jeffbolznv vulkan: more FA details in vk_perf_logger
813d43e3
jeffbolznv vulkan: Use fewer rows for scalar FA when HS is not a multiple of 16
f6ed9e0f
jeffbolznv jeffbolznv requested a review from slaren slaren 17 days ago
jeffbolznv jeffbolznv requested a review from 0cc4m 0cc4m 17 days ago
github-actions github-actions added testing
github-actions github-actions added Vulkan
github-actions github-actions added ggml
0cc4m
0cc4m approved these changes on 2025-11-25
0cc4m 0cc4m merged d414db02 into master 16 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone