llama : refactor llama_model_loader (WIP)

wip : remove ggml_ctx from llama_model_loader wip : merge gguf_file_loader in llama_model_loader
ggerganov · Aug 16, 2023 · 5339b85 · 5339b85
1 parent 23248d7
commit 5339b85
Show file tree

Hide file tree

Showing 3 changed files with 208 additions and 249 deletions.
diff --git a/ggml.c b/ggml.c
@@ -19065,14 +19065,6 @@ enum gguf_type gguf_get_arr_type(struct gguf_context * ctx, int i) {
     return ctx->kv[i].value.arr.type;
 }
 
-int32_t gguf_get_arr_i32(struct gguf_context * ctx, int key_id, int i) {
-    return ((int32_t *) ctx->kv[key_id].value.arr.data)[i];
-}
-
-float gguf_get_arr_f32(struct gguf_context * ctx, int key_id, int i) {
-    return ((float *) ctx->kv[key_id].value.arr.data)[i];
-}
-
 const void * gguf_get_arr_data(struct gguf_context * ctx, int i) {
     return ctx->kv[i].value.arr.data;
 }

diff --git a/ggml.h b/ggml.h
@@ -1499,7 +1499,6 @@ extern "C" {
             struct ggml_context * ctx,
             struct ggml_tensor  * tensor);
 
-
     GGML_API void ggml_build_forward_expand(struct ggml_cgraph * cgraph, struct ggml_tensor * tensor);
 
     GGML_API struct ggml_cgraph ggml_build_forward (struct ggml_tensor * tensor);