Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	pyproject.toml
#	requirements/requirements-convert_legacy_llama.txt
#	src/CMakeLists.txt
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp

src/llama-kv-cache.cpp

@@ -974,6 +974,10 @@ void llama_kv_cache::apply_ubatch(const slot_info & sinfo, const llama_ubatch &
 }
 
 bool llama_kv_cache::get_can_shift() const {
+    // Step35 uses per-layer RoPE dims; K-shift assumes a single global n_rot.
+    if (model.arch == LLM_ARCH_STEP35) {
+        return false;
+    }
     return true;
 }