ggml : update ggml_backend_cpu_device_supports_op (llama/10867)

* ggml : fix cpy op for IQ-quants to use reference impl

ggml-ci

* ggml : disable tests involving i-matrix quantization

* ggml : update ggml_backend_cpu_device_supports_op

ggml-ci

diff --git a/ggml/src/ggml-cpu/ggml-cpu.cpp b/ggml/src/ggml-cpu/ggml-cpu.cpp
index c390957afa8e3230c0d612315676b470acea65fe..0b6419f83f0c202ff33f5bbc58529e35b819252e 100644 (file)
--- a/ggml/src/ggml-cpu/ggml-cpu.cpp
+++ b/ggml/src/ggml-cpu/ggml-cpu.cpp
@@ -394,8 +394,11 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
     switch (op->op) {
         case GGML_OP_CPY:
             return
+                op->type != GGML_TYPE_IQ3_XXS &&
+                op->type != GGML_TYPE_IQ3_S   &&
                 op->type != GGML_TYPE_IQ2_XXS &&
                 op->type != GGML_TYPE_IQ2_XS  &&
+                op->type != GGML_TYPE_IQ2_S   &&
                 op->type != GGML_TYPE_IQ1_S   &&
                 op->type != GGML_TYPE_IQ1_M; // missing type_traits.from_float
         case GGML_OP_MUL_MAT: