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 fb77399 commit 18cd2f8Copy full SHA for 18cd2f8
vllm_ascend/worker/npu_input_batch.py
@@ -69,6 +69,7 @@ class CachedRequestState:
69
prompt_embeds: Optional[torch.Tensor] = None
70
71
prev_num_draft_len: int = 0 # previous number of draft tokens
72
+
73
def __post_init__(self):
74
self.num_prompt_tokens = length_from_prompt_token_ids_or_embeds(
75
self.prompt_token_ids, self.prompt_embeds)
0 commit comments