[Minor] Fix styles for overlap mode (#2068)

2024-11-17 19:49:20 -08:00
parent 8c280cee55
commit a9e90b4bce
4 changed files with 8 additions and 17 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -276,10 +276,6 @@ class ModelRunner:
            else None
        )
        self.dtype = self.vllm_model_config.dtype
-        if self.sliding_window_size:
-            assert (
-                self.server_args.attention_backend == "flashinfer"
-            ), "Only flashinfer supports window attention."

        logger.info(
            f"Load weight end. "