Merge commit '64eda5deb9' into concedo_experimental

# Conflicts:
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	README.md
#	docs/backend/SYCL.md
#	examples/llava/clip.cpp
#	examples/server_embd.py
#	ggml/src/ggml-cann/acl_tensor.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	src/CMakeLists.txt
#	tests/test-chat-template.cpp

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -4211,6 +4211,12 @@ static uint32_t ggml_vk_guess_split_k(ggml_backend_vk_context * ctx, int m, int
             if (split_k == 3) {
                 split_k = 2;
             }
+            if (ctx->device->coopmat2) {
+                // coopmat2 shader expects splits to be aligned to 256
+                while (split_k > 1 && ((k / split_k) % 256) != 0) {
+                    split_k /= 2;
+                }
+            }
         }
     }