llama.cpp
opencl: fix q6_K flat mul_mat for Adreno A6x/A7x GPUs with older E031 compilers
#26476

Merged

opencl: fix q6_K flat mul_mat for Adreno A6x/A7x GPUs with older E031 compilers #26476

lhez merged 2 commits into ggml-org:master from qualcomm:hq/a7x-q6k-gated-r0730

github-actions added ggml

github-actions added OpenCL

opencl: decline KV-convert flash_attn variants on Adreno A7X (compile…

a6b70929

opencl: fix q6_K flat mul_mat on older Adreno E031 compilers, gated

6ee92622

wanghqc force pushed to 6ee92622 77 days ago

lhez marked this pull request as ready for review 66 days ago

lhez requested a review 66 days ago

max-krasnyansky approved these changes on 2026-08-20

lhez approved these changes on 2026-08-20

lhez merged 6503355d into master 65 days ago

Reviewers

lhez

max-krasnyansky

Assignees

No one assigned

Labels

ggml OpenCL

Milestone

No milestone