diff --git a/python/sglang/srt/model_executor/cuda_graph_runner.py b/python/sglang/srt/model_executor/cuda_graph_runner.py index 612b4d243..80f8c6564 100644 --- a/python/sglang/srt/model_executor/cuda_graph_runner.py +++ b/python/sglang/srt/model_executor/cuda_graph_runner.py @@ -323,11 +323,11 @@ class CudaGraphRunner: self.pp_proxy_tensors = { "hidden_states": torch.zeros( (self.max_bs, self.model_runner.model_config.hidden_size), - dtype=torch.bfloat16, + dtype=self.model_runner.model_config.dtype, ), "residual": torch.zeros( (self.max_bs, self.model_runner.model_config.hidden_size), - dtype=torch.bfloat16, + dtype=self.model_runner.model_config.dtype, ), }