Update deprecated type hinting in models (#18132)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -1,7 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Tuple
|
||||
|
||||
import torch
|
||||
|
||||
@@ -25,8 +24,8 @@ class MambaCacheParams:
|
||||
class MambaCacheManager(ConstantSizeCache):
|
||||
|
||||
def __init__(self, vllm_config: VllmConfig, dtype: torch.dtype,
|
||||
num_mamba_layers: int, conv_state_shape: Tuple[int, int],
|
||||
temporal_state_shape: Tuple[int, int]):
|
||||
num_mamba_layers: int, conv_state_shape: tuple[int, int],
|
||||
temporal_state_shape: tuple[int, int]):
|
||||
|
||||
# Determine max batch size to set size of MambaCache
|
||||
max_batch_size = vllm_config.scheduler_config.max_num_seqs
|
||||
|
||||
Reference in New Issue
Block a user