Higher priority for user input of max_prefill_tokens & format (#540)
This commit is contained in:
@@ -1,4 +1,5 @@
|
||||
"""Logits processing."""
|
||||
|
||||
import torch
|
||||
from torch import nn
|
||||
from vllm.distributed import (
|
||||
|
||||
Reference in New Issue
Block a user