Merge commit '64eda5deb9859e87a020e56bab5d2f9ca956f1de' 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

src/llama-graph.cpp

@@ -1215,6 +1215,15 @@ ggml_tensor * llm_graph_context::build_attn_mha(
             v = ggml_transpose(ctx0, v);
         }
 
+        // this can happen when KV cache is not used (e.g. an embedding model with non-causal attn)
+        if (k->type == GGML_TYPE_F32) {
+            k = ggml_cast(ctx0, k, GGML_TYPE_F16);
+        }
+
+        if (v->type == GGML_TYPE_F32) {
+            v = ggml_cast(ctx0, v, GGML_TYPE_F16);
+        }
+
         cur = ggml_flash_attn_ext(ctx0, q, k, v, kq_mask, kq_scale, hparams.f_max_alibi_bias,
                                   hparams.attn_soft_cap ? hparams.f_attn_logit_softcapping : 0.0f);