ggml : initial ARM_NEON 2x F16 Q4_0 implementation

Author: ggerganov

Makefile

@@ -31,10 +31,15 @@ endif
 #
 
 # keep standard at C11 and C++11
-CFLAGS   = -I.              -O3 -DNDEBUG -std=c11   -fPIC
-CXXFLAGS = -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC
+CFLAGS   = -I.              -O3 -std=c11   -fPIC
+CXXFLAGS = -I. -I./examples -O3 -std=c++11 -fPIC
 LDFLAGS  =
 
+ifndef LLAMA_NO_NDEBUG
+	CFLAGS   += -DNDEBUG
+	CXXFLAGS += -DNDEBUG
+endif
+
 # warnings
 CFLAGS   += -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function
 CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar

examples/quantize-stats/quantize-stats.cpp

@@ -221,7 +221,7 @@ int main(int argc, char ** argv) {
                 break;
             }
             int j;
-            for (j = 0; j < GGML_TYPE_COUNT && strcmp(argv[i], ggml_type_name((ggml_type) i)) != 0; j++) {
+            for (j = 0; j < GGML_TYPE_COUNT && strcmp(argv[i], ggml_type_name((ggml_type) j)) != 0; j++) {
                 // find match
             }
             if (j < GGML_TYPE_COUNT) {