From e6447cd24acbde845dbb4aa27acfd4c17b5c849c Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Mon, 11 Aug 2025 17:42:35 -0700
Subject: [PATCH] mtmd: Update the llama-server request

---
 modules/llama_cpp_server.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/modules/llama_cpp_server.py b/modules/llama_cpp_server.py
index 58534f26..e82edb90 100644
--- a/modules/llama_cpp_server.py
+++ b/modules/llama_cpp_server.py
@@ -149,11 +149,10 @@ class LlamaServer:
             IMAGE_TOKEN_COST_ESTIMATE = 600  # A safe, conservative estimate per image
 
             base64_images = [convert_pil_to_base64(img) for img in pil_images]
-            multimodal_prompt_object = {
-                "prompt": prompt,
+            payload["prompt"] = {
+                "prompt_string": prompt,
                 "multimodal_data": base64_images
             }
-            payload["prompt"] = multimodal_prompt_object
 
             # Calculate an estimated token count
             text_tokens = self.encode(prompt, add_bos_token=state["add_bos_token"])