fix

noooop · noooop · commit 4e16bb9c4261 · 2025-07-14T14:07:07.000+08:00
Signed-off-by: wang.yuqi &lt;noooop@126.com&gt;
diff --git a/examples/offline_inference/qwen_1m.py b/examples/offline_inference/qwen_1m.py
@@ -56,7 +56,7 @@ def initialize_engine(max_model_len=1048576) -> LLM:
         enforce_eager=True,
         enable_chunked_prefill=True,
         max_num_batched_tokens=131072,
-        hf_overrides={"max_position_embeddings": max_model_len}
+        hf_overrides={"max_position_embeddings": max_model_len},
     )
     return llm
 

Original file line number	Diff line number	Diff line change
`@@ -56,7 +56,7 @@ def initialize_engine(max_model_len=1048576) -> LLM:`
`56`	`56`	`enforce_eager=True,`
`57`	`57`	`enable_chunked_prefill=True,`
`58`	`58`	`max_num_batched_tokens=131072,`
`59`		`- hf_overrides={"max_position_embeddings": max_model_len}`
	`59`	`+ hf_overrides={"max_position_embeddings": max_model_len},`
`60`	`60`	`)`
`61`	`61`	`return llm`
`62`	`62`