[Spec Decode] Unified Parallel Drafting (#32887)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
This commit is contained in:
committed by
GitHub
parent
5b2a9422f0
commit
af3162d3aa
@@ -204,7 +204,7 @@ def test_mtp_propose(num_speculative_tokens, monkeypatch):
|
||||
target_positions=target_positions,
|
||||
target_hidden_states=target_hidden_states,
|
||||
next_token_ids=next_token_ids,
|
||||
last_token_indices=None,
|
||||
token_indices_to_sample=None,
|
||||
common_attn_metadata=common_attn_metadata,
|
||||
sampling_metadata=sampling_metadata,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user