Skip to content

vulkan: MMQ Workaround for legacy Windows AMD driver bug#17285

Merged
0cc4m merged 1 commit intomasterfrom
0cc4m/vulkan-mmq-amd-windows-workaround
Nov 15, 2025
Merged

vulkan: MMQ Workaround for legacy Windows AMD driver bug#17285
0cc4m merged 1 commit intomasterfrom
0cc4m/vulkan-mmq-amd-windows-workaround

Conversation

@0cc4m
Copy link
Collaborator

@0cc4m 0cc4m commented Nov 15, 2025

I'm not happy this is still a problem, but as @netrunnereve predicted, there are people that have to use old Windows AMD drivers affected by the 16-bit unpack8 bug.

I don't see a performance difference from this, just uglier code.

@0cc4m 0cc4m requested a review from jeffbolznv November 15, 2025 11:52
@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 Nov 15, 2025
@0cc4m 0cc4m merged commit 4dca015 into master Nov 15, 2025
3 checks passed
@0cc4m 0cc4m deleted the 0cc4m/vulkan-mmq-amd-windows-workaround branch November 15, 2025 14:19
Anico2 added a commit to Anico2/llama.cpp that referenced this pull request Jan 15, 2026
blime4 referenced this pull request in blime4/llama.cpp Feb 5, 2026
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.

2 participants