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 2c6202a commit 7378283Copy full SHA for 7378283
vllm_ascend/worker/model_runner_v1.py
@@ -594,7 +594,7 @@ def _set_up_drafter(self):
594
self.discard_request_indices = self._make_buffer(self.max_num_reqs,
595
dtype=torch.int64)
596
self.num_discarded_requests = 0
597
-
+
598
def _get_drafter(self):
599
return get_spec_decode_method(self.speculative_config.method,
600
self.vllm_config, self.device, self)
0 commit comments