From 8d2d876fc8ec690db8728d363c593174ee3b97c0 Mon Sep 17 00:00:00 2001 From: Ying Sheng Date: Wed, 14 Aug 2024 21:56:01 -0700 Subject: [PATCH] [Fix] fix the typo bug for window attention (#1106) --- python/sglang/srt/model_executor/model_runner.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/sglang/srt/model_executor/model_runner.py b/python/sglang/srt/model_executor/model_runner.py index 6826bf1a4..675ca60d0 100644 --- a/python/sglang/srt/model_executor/model_runner.py +++ b/python/sglang/srt/model_executor/model_runner.py @@ -337,7 +337,7 @@ class ModelRunner: use_tensor_cores=use_tensor_cores, ) else: - self.flashinfer_workspace_buffers = torch.empty( + self.flashinfer_workspace_buffer = torch.empty( global_config.flashinfer_workspace_size, dtype=torch.uint8, device="cuda",