ggml : add Q4_3 quantization (ggerganov#1082)

bnikolic · Apr 20, 2023 · e0305ea · e0305ea
1 parent 6a9661e
commit e0305ea
Show file tree

Hide file tree

Showing 5 changed files with 293 additions and 37 deletions.
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
@@ -15,6 +15,7 @@ int main(int argc, char ** argv) {
         fprintf(stderr, "  type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0);
         fprintf(stderr, "  type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
         fprintf(stderr, "  type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2);
+        fprintf(stderr, "  type = %d - q4_3\n", LLAMA_FTYPE_MOSTLY_Q4_3);
         return 1;
     }