LLM inference in C/C++
C++ ggml
kleidiai : warn once when a weight type has no KleidiAI kernel (#25701)
Kamalesh VSfb0e6b621917
diff --git a/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp b/ggml/src/ggml-cpu/kleidiai/kleidiai.cppindex 5cdcbdfe4c..1c5a459f21 100644--- a/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp+++ b/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp@@ -1719,6 +1719,7 @@ class extra_buffer_type : ggml::cpu::extra_buffer_type {return true;}+return false;}@@ -1727,6 +1728,20 @@ class extra_buffer_type : ggml::cpu::extra_buffer_type {if (op->src[0]->buffer && op->src[0]->buffer->buft == ggml_backend_cpu_kleidiai_buffer_type()) {return (ggml::cpu::tensor_traits *) op->src[0]->extra;} else {+ // KleidiAI only has kernels for Q4_0 and Q8_0. For a quantized weight of any+ // other type (K-quants, IQ) it declines the op and returns nullptr below, so+ // KleidiAI does not accelerate it. Another CPU backend may still take the op,+ // and this can run during graph planning, so the message says what KleidiAI+ // did rather than what ends up executing. Warn once per process.+ if (ggml_is_quantized(op->src[0]->type) &&+ op->src[0]->type != GGML_TYPE_Q4_0 && op->src[0]->type != GGML_TYPE_Q8_0) {+ static std::atomic<bool> warned(false);+ if (!warned.exchange(true)) {+ GGML_LOG_WARN("kleidiai: no kernel for tensor type %s, not accelerated by KleidiAI "+ "(kernels available for Q4_0 and Q8_0)\n",+ ggml_type_name(op->src[0]->type));+ }+ }if (op->src[0]->type != GGML_TYPE_F16) {return nullptr;}