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 <ggerganov@gmail.com>

1 files changed, 1 insertions, 2 deletions

diff --git a/llama.h b/llama.h
index ebf55f4..d3f4cae 100644
--- a/llama.h
+++ b/llama.h
@@ -81,8 +81,7 @@ extern "C" {
     LLAMA_API int llama_model_quantize(
             const char * fname_inp,
             const char * fname_out,
-                   int   itype,
-                   int   qk);
+                   int   itype);
 
     // Run the llama inference to obtain the logits and probabilities for the next token.
     // tokens + n_tokens is the provided batch of new tokens to process