ggml : introduce structs for the q4 data blocks (#356)

* Introduce structs for the q4 data blocks * ggml : rename quant struct variables + fix ARM_NEON --------- Co-authored-by: Georgi Gerganov <[email protected]>
ggerganov · Mar 28, 2023 · c1f8850 · c1f8850
1 parent e067026
commit c1f8850
Show file tree

Hide file tree

Showing 6 changed files with 150 additions and 235 deletions.
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
@@ -4,8 +4,6 @@
 #include <cstdio>
 #include <string>
 
-const int QK = 32;
-
 // usage:
 //  ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
 //
@@ -39,7 +37,7 @@ int main(int argc, char ** argv) {
     {
         const int64_t t_start_us = ggml_time_us();
 
-        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype, QK)) {
+        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype)) {
             fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
             return 1;
         }