Fixes crash when K/V rotation buffer is unallocated in speculative
Llama fixes crash in speculative decoding when K/V rotation buffer is unallocated by adding null buffer guards.
llama : add guard for K/V rotation input when buffer is unallocated (#25215) llm_graph_input_attn_kv::set_input and llm_graph_input_attn_kv_iswa::set_input call set_input_k_rot / set_input_v_rot whenever the rotation tensor pointer is non-null, but the tensor's buffer can be unallocated (NULL) when a graph only stores K/V without attending -- e.g. DFlash speculative decoding's KV-injection pass. set_input_k_rot then calls ggml_backend_buffer_is_host() on a NULL buffer and aborts with GGML_ASSERT(buffer). Guard the four k_rot/v_rot inputs with the same "&& ->buffer" check that the adjacent kq_mask inputs already use in these two functions.
When the buffer is unallocated there is no data to upload, so skipping is correct. Fixes #25191 Signed-off-by: liminfei-amd macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16) Android: Android arm64 (CPU) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows arm64 (OpenCL Adreno)…
- github.comllama.cpp b9873primary