Update attn_qkv schema, change throw behaviour

src/llama-quant.cpp

@@ -355,7 +355,7 @@ static ggml_type tensor_type_fallback(quantize_state_impl & qs, const ggml_tenso
     return return_type;
 }
 
-ggml_type llama_tensor_get_type_impl(quantize_state_impl & qs, ggml_type new_type, const ggml_tensor * tensor, llama_ftype ftype, tensor_category category) {
+static ggml_type llama_tensor_get_type_impl(quantize_state_impl & qs, ggml_type new_type, const ggml_tensor * tensor, llama_ftype ftype, tensor_category category) {
     const std::string name = ggml_get_name(tensor);
 
     // TODO: avoid hardcoded tensor names - use the TN_* constants
@@ -782,7 +782,7 @@ ggml_type llama_ftype_get_default_type(llama_ftype ftype) {
         case LLAMA_FTYPE_MOSTLY_IQ3_S:
         case LLAMA_FTYPE_MOSTLY_IQ3_M:   return GGML_TYPE_IQ3_S;
 
-        default: throw std::runtime_error(format("invalid output file type %d\n", ftype));
+        default: return GGML_TYPE_COUNT;
     }
 }
 
@@ -874,6 +874,9 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
     }
 
     ggml_type default_type = llama_ftype_get_default_type(ftype);
+    if (default_type == GGML_TYPE_COUNT) {
+        throw std::runtime_error(format("invalid output file type %d\n", ftype));
+    }
 
     // mmap consistently increases speed on Linux, and also increases speed on Windows with
     // hot cache. It may cause a slowdown on macOS, possibly related to free memory.