Skip to content

Vulkan: Fix the memory allocation change in #17110#17122

Merged
0cc4m merged 1 commit into
masterfrom
0cc4m/vulkan-memory-reporting-fix-fix
Nov 9, 2025
Merged

Vulkan: Fix the memory allocation change in #17110#17122
0cc4m merged 1 commit into
masterfrom
0cc4m/vulkan-memory-reporting-fix-fix

Conversation

@0cc4m
Copy link
Copy Markdown
Contributor

@0cc4m 0cc4m commented Nov 9, 2025

I forgot to exit the second loop early in #17110. This should fix #17117.

@0cc4m 0cc4m requested a review from ngxson as a code owner November 9, 2025 14:52
@0cc4m 0cc4m changed the title Vulkan: Fix the memory allocation change in Vulkan: Fix the memory allocation change in #17110 Nov 9, 2025
@0cc4m 0cc4m force-pushed the 0cc4m/vulkan-memory-reporting-fix-fix branch from de6d775 to 0d5e75d Compare November 9, 2025 14:54
@0cc4m 0cc4m requested review from jeffbolznv and removed request for ngxson November 9, 2025 14:54
@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 9, 2025
@0cc4m 0cc4m merged commit 392e09a into master Nov 9, 2025
59 of 63 checks passed
@0cc4m 0cc4m deleted the 0cc4m/vulkan-memory-reporting-fix-fix branch November 9, 2025 15:14
@Goldenkoron
Copy link
Copy Markdown

Goldenkoron commented Nov 9, 2025

On strix halo, trying to load any model on windows with 96gb set in UMA will give a memory buffer error, seemingly no matter the allocation size.

With 64gb set, models will try to load up to 96gb but if the memory actually exceeds 64gb it will give a device out of memory error (even if there is room in Windows shared memory, it never uses it).

image image

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
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
ljubomirj pushed a commit to ljubomirj/llama.cpp that referenced this pull request May 6, 2026
my-other-github-account pushed a commit to my-other-github-account/llama.cpp that referenced this pull request May 15, 2026
my-other-github-account pushed a commit to my-other-github-account/llama.cpp that referenced this pull request May 15, 2026
phibya pushed a commit to ziee-ai/llama.cpp that referenced this pull request May 29, 2026
fewtarius pushed a commit to fewtarius/llama.cpp that referenced this pull request May 30, 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.

Misc. bug: b6996 need too much memory

3 participants