Skip to content

Conversation

lhez
Copy link
Collaborator

@lhez lhez commented Sep 12, 2025

In concat, the data type for ne in the host code could be inconsistent with the kernels, depending sizeof(long). It works fine on Android, Linux and Windows x64, but crashes on Windows arm64 with Adreno with -51 (CL_INVALID_ARG_SIZE). This PR uses cl_long to make sure data type is consistent.

@github-actions github-actions bot added ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend labels Sep 12, 2025
@lhez lhez marked this pull request as ready for review September 12, 2025 06:09
@lhez lhez force-pushed the concat-win-arm64-fix branch from eaf86e3 to cad982a Compare September 16, 2025 03:24
@lhez lhez force-pushed the concat-win-arm64-fix branch from cad982a to b84d6ba Compare September 18, 2025 05:36
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 OpenCL Issues specific to the OpenCL backend
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant