hotfix for rwkv

ggml.h

@@ -194,7 +194,7 @@
 #define GGML_QNT_VERSION_FACTOR 1000 // do not change this
 
 #define GGML_MAX_DIMS          4
-#define GGML_MAX_NODES         4096
+#define GGML_MAX_NODES         8192
 #define GGML_MAX_PARAMS        256
 #define GGML_MAX_CONTEXTS      64
 #define GGML_MAX_OPT           4

gpttype_adapter.cpp

@@ -479,7 +479,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
         }
         else
         {
-            n_batch = 10; //use sequence mode to speedup
+            n_batch = 8; //use sequence mode to speedup
 
             //setup buffers for rwkv state
             auto padding = 512u;

koboldcpp.py

@@ -224,7 +224,7 @@ maxctx = 2048
 maxlen = 256
 modelbusy = False
 defaultport = 5001
-KcppVersion = "1.30"
+KcppVersion = "1.30.1"
 
 class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
     sys_version = ""