init

Signed-off-by: Avery Yingyi Huang <[email protected]>

Author: yyihuang

vllm/v1/attention/backends/flashinfer.py

@@ -251,7 +251,7 @@ def __init__(self, kv_cache_spec: AttentionSpec, layer_names: list[str],
 
     def _get_workspace_buffer(self):
         if self._workspace_buffer is None:
-            self._workspace_buffer = torch.empty(
+            self._workspace_buffer = torch.zeros(
                 FLASHINFER_WORKSPACE_BUFFER_SIZE,
                 dtype=torch.uint8,
                 device=self.device)