minor

Edwardf0t1 · Edwardf0t1 · commit f9b88fdbf3eb · 2025-10-24T03:19:27.000Z
Signed-off-by: Zhiyu Cheng &lt;zhiyuc@nvidia.com&gt;
diff --git a/examples/llm_ptq/hf_ptq.py b/examples/llm_ptq/hf_ptq.py
@@ -836,7 +836,7 @@ def output_decode(generated_ids, input_shape):
             "Specify the attention implementation to use. "
             "This arg will be passed to the HF model loading if specified."
         ),
-        default="eager",
+        default=None,
         type=str,
     )
 

Original file line number	Diff line number	Diff line change
`@@ -836,7 +836,7 @@ def output_decode(generated_ids, input_shape):`
`836`	`836`	`"Specify the attention implementation to use. "`
`837`	`837`	`"This arg will be passed to the HF model loading if specified."`
`838`	`838`	`),`
`839`		`- default="eager",`
	`839`	`+ default=None,`
`840`	`840`	`type=str,`
`841`	`841`	`)`
`842`	`842`