Skip to content

vulkan: fix assertion when qy_needs_dequant #12068

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Feb 25, 2025
Merged

vulkan: fix assertion when qy_needs_dequant #12068

merged 1 commit into from
Feb 25, 2025

Conversation

@jeffbolznv
Copy link
Collaborator

@jeffbolznv jeffbolznv commented Feb 25, 2025

Looks like a copy/paste bug from qx_needs_dequant.

llama-cli -no-cnv -p "Write a function in C to compute the fibonacci sequence" -ngl 99 -m C:\models\Moonlight-16B-A3B-Instruct-Q4_K_M.gguf
...
C:\github\jeffbolznv\llama.cpp\ggml\src\ggml-vulkan\ggml-vulkan.cpp:4772: GGML_ASSERT(d_Y->size >= y_sz * ne02 * ne03) failed

@jeffbolznv
vulkan: fix assertion when qy_needs_dequant
ed52509 
Looks like a copy/paste bug from qx_needs_dequant.
@jeffbolznv jeffbolznv requested a review from 0cc4m February 25, 2025 14:14
0cc4m
0cc4m approved these changes Feb 25, 2025
View reviewed changes
Copy link
Collaborator

@0cc4m 0cc4m left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not necessarily a copy-paste error. The function went through tons of iterations in the past, maybe it was correct at some point, but definitely not anymore.

@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 Feb 25, 2025
@0cc4m 0cc4m merged commit a82c9e7 into ggml-org:master Feb 25, 2025
47 checks passed
orca-zhang pushed a commit to orca-zhang/llama.cpp that referenced this pull request Feb 26, 2025
@jeffbolznv @orca-zhang
vulkan: fix assertion when qy_needs_dequant (ggml-org#12068)
2e02087 
Looks like a copy/paste bug from qx_needs_dequant.
mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025
@jeffbolznv @mglambda
vulkan: fix assertion when qy_needs_dequant (ggml-org#12068)
e816b9b 
Looks like a copy/paste bug from qx_needs_dequant.
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Mar 19, 2025
@jeffbolznv @arthw
vulkan: fix assertion when qy_needs_dequant (ggml-org#12068)
e1fd56d 
Looks like a copy/paste bug from qx_needs_dequant.
mostlyuseful pushed a commit to mostlyuseful/llama.cpp that referenced this pull request May 12, 2025
@jeffbolznv @mostlyuseful
vulkan: fix assertion when qy_needs_dequant (ggml-org#12068)
6dfca6c 
Looks like a copy/paste bug from qx_needs_dequant.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@0cc4m 0cc4m 0cc4m approved these changes

Assignees

No one assigned

Labels

ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@jeffbolznv @0cc4m