point to 0.8.3 branch

Signed-off-by: Roger Wang <[email protected]>

Author: ywang96

_posts/2025-04-05-llama4.md

@@ -56,7 +56,7 @@ vllm serve meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 \
 ```
 **Multimodality:**
 
-The Llama 4 models excel at image understanding up to 8-10 images. By default, vLLM server accepts 1 image per request. Please pass `--limit-mm-per-prompt image=10` to serve up to 10 images per request with OpenAI-compatible API. We also recommend checking out our multi-image offline inference example with Llama-4 [here](https://github.com/vllm-project/vllm/blob/main/examples/offline_inference/vision_language_multi_image.py).
+The Llama 4 models excel at image understanding up to 8-10 images. By default, vLLM server accepts 1 image per request. Please pass `--limit-mm-per-prompt image=10` to serve up to 10 images per request with OpenAI-compatible API. We also recommend checking out our multi-image offline inference example with Llama-4 [here](https://github.com/vllm-project/vllm/blob/v0.8.3/examples/offline_inference/vision_language_multi_image.py).
 
 **Performance:**