diff --git a/docs/source/models/generative_models.md b/docs/source/models/generative_models.md
index 63fc53b0e7c5..3291006ed668 100644
--- a/docs/source/models/generative_models.md
+++ b/docs/source/models/generative_models.md
@@ -59,7 +59,7 @@ A code example can be found here: <gh-file:examples/offline_inference/basic/basi
 
 ### `LLM.beam_search`
 
-The {class}`~vllm.LLM.beam_search` method implements [beam search](https://huggingface.co/docs/transformers/en/generation_strategies#beam-search-decoding) on top of {class}`~vllm.LLM.generate`.
+The {class}`~vllm.LLM.beam_search` method implements [beam search](https://huggingface.co/docs/transformers/en/generation_strategies#beam-search) on top of {class}`~vllm.LLM.generate`.
 For example, to search using 5 beams and output at most 50 tokens:
 
 ```python
diff --git a/docs/source/models/supported_models.md b/docs/source/models/supported_models.md
index d65b205826f7..b13ec92957a1 100644
--- a/docs/source/models/supported_models.md
+++ b/docs/source/models/supported_models.md
@@ -793,6 +793,8 @@ or `--limit-mm-per-prompt` (online serving). For example, to enable passing up t
 Offline inference:
 
 ```python
+from vllm import LLM
+
 llm = LLM(
     model="Qwen/Qwen2-VL-7B-Instruct",
     limit_mm_per_prompt={"image": 4},