[Misc] unify variable for LLM instance (#20996)

Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-07-21 19:18:33 +08:00
parent e6b90a2805
commit d97841078b
53 changed files with 237 additions and 236 deletions
--- a/docs/models/pooling_models.md
+++ b/docs/models/pooling_models.md
@@ -174,11 +174,11 @@ You can change the output dimensions of embedding models that support Matryoshka
 ```python
 from vllm import LLM, PoolingParams

-model = LLM(model="jinaai/jina-embeddings-v3", 
-            task="embed", 
-            trust_remote_code=True)
-outputs = model.embed(["Follow the white rabbit."], 
-                      pooling_params=PoolingParams(dimensions=32))
+llm = LLM(model="jinaai/jina-embeddings-v3",
+          task="embed",
+          trust_remote_code=True)
+outputs = llm.embed(["Follow the white rabbit."],
+                    pooling_params=PoolingParams(dimensions=32))
 print(outputs[0].outputs)
 ```