llama.cpp
vulkan: FA MMQ should use fp32 for Q quantization calculations
#27413
Merged
Overview
Commits
1
Changes
View On GitHub

vulkan: FA MMQ should use fp32 for Q quantization calculations #27413

jeffbolznv merged 1 commit into ggml-org:master from jeffbolznv:fa_mmq_fp32
jeffbolznv
jeffbolznv vulkan: FA MMQ should use fp32 for Q quantization calculations
5c2cd5cc
jeffbolznv jeffbolznv requested a review 65 days ago
github-actions github-actions added Vulkan
github-actions github-actions added ggml
ggerganov
ggerganov approved these changes on 2026-08-20
0cc4m
0cc4m approved these changes on 2026-08-20
jeffbolznv jeffbolznv merged 78ec4c37 into master 64 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Vulkan ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum