fix: Clear kv cache to avoid kv bug when image is evaluated first

Author: abetlen

llama_cpp/llama_chat_format.py

@@ -2637,6 +2637,7 @@ def embed_image_bytes(image_bytes: bytes):
 
         # Evaluate prompt
         llama.reset()
+        llama._ctx.kv_cache_clear()
         for type_, value in split_text:
             if type_ == "text":
                 tokens = llama.tokenize(value.encode("utf8"), add_bos=False, special=True)