[Spec Decode] Make propose_draft_token_ids non-blocking for lower TTFT (#23041)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
@@ -200,7 +200,6 @@ def create_model_runner_output(
|
||||
req_ids=req_ids,
|
||||
req_id_to_index=req_id_to_index,
|
||||
sampled_token_ids=sampled_token_ids,
|
||||
spec_token_ids=None,
|
||||
logprobs=None,
|
||||
prompt_logprobs_dict={},
|
||||
pooler_output=None,
|
||||
|
||||
Reference in New Issue
Block a user