Update documentation for new completion parameter

Author: 65a

tools/server/README.md

@@ -226,6 +226,7 @@ services:
 ### Multimodal support
 
 Multimodal support was added in [#12898](https://github.com/ggml-org/llama.cpp/pull/12898) and is currently an experimental feature.
+It is currently available in the non-OAI-compatible completion endpoint, and the OAI-compatible chat endpoint.
 
 For more details, please refer to [multimodal documentation](../../docs/multimodal.md)
 
@@ -407,6 +408,8 @@ Multiple prompts are also supported. In this case, the completion result will be
   - Strings and sequences of tokens: `["string1", [12, 34, 56]]`
   - Mixed types: `[[12, 34, "string", 56, 78], [12, 34, 56], "string"]`
 
+`multimodal_data`: Optional. Should be an array of strings, containing base64 encoded multimodal data (e.g. images, audio). There must be an identical number of MTMD media markers in the raw prompt which act as placeholders for the data provided to this parameter. The multimodal data files will be substituted in order.
+
 `temperature`: Adjust the randomness of the generated text. Default: `0.8`
 
 `dynatemp_range`: Dynamic temperature range. The final temperature will be in the range of `[temperature - dynatemp_range; temperature + dynatemp_range]` Default: `0.0`, which is disabled.