We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent c7a74a6 commit f1ddce2Copy full SHA for f1ddce2
vllm_ascend/worker/worker_v1.py
@@ -248,9 +248,10 @@ def pin_lora(self, lora_id: int) -> bool:
248
def execute_dummy_batch(self) -> None:
249
runner = self.model_runner
250
if runner.dp_size <= 1:
251
- raise ValueError("Dummy batch execution should only be "
252
- "performed with data parallelism enabled, but got "
253
- f"dp_size={runner.dp_size}.")
+ raise ValueError(
+ "Dummy batch execution should only be "
+ "performed with data parallelism enabled, but got "
254
+ f"dp_size={runner.dp_size}.")
255
256
# If torchair graph is enabled, notify the other DP ranks that this is a
257
# dummy run by using '-1' as a flag for num_tokens. This will be
0 commit comments