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
@lhez lhez merged commit 51f5a45 into ggml-org:master Sep 21, 2025
95 of 96 checks passed
struct pushed a commit to struct/llama.cpp that referenced this pull request Sep 26, 2025
yael-works pushed a commit to yael-works/llama.cpp that referenced this pull request Oct 15, 2025
pwilkin pushed a commit to pwilkin/llama.cpp that referenced this pull request Oct 23, 2025
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.

2 participants