llama : add gguf_remove_key + remove split meta during quantize (#6591)

* Remove split metadata when quantize model shards

* Find metadata key by enum

* Correct loop range for gguf_remove_key and code format

* Free kv memory

---------

Co-authored-by: z5269887 <z5269887@unsw.edu.au>

1 files changed, 4 insertions, 0 deletions

diff --git a/llama.cpp b/llama.cpp
index dad2c4fb..83dd55ef 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -13535,6 +13535,10 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
     gguf_set_kv     (ctx_out, ml.meta);
     gguf_set_val_u32(ctx_out, "general.quantization_version", GGML_QNT_VERSION);
     gguf_set_val_u32(ctx_out, "general.file_type", ftype);
+    // Remove split metadata
+    gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_NO).c_str());
+    gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_COUNT).c_str());
+    gguf_remove_key(ctx_out, ml.llm_kv(LLM_KV_SPLIT_TENSORS_COUNT).c_str());
 
     if (params->kv_overrides) {
         const std::vector<llama_model_kv_override> & overrides = *(const std::vector<llama_model_kv_override> *)params->kv_overrides;