biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Update deprecated type hinting in model_executor/layers (#18056)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-13 12:17:23 +01:00
committed by GitHub
parent 906f0598fc
commit 6223dd8114
87 changed files with 523 additions and 523 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/model_executor/layers/quantization/utils/marlin_utils.py
View File

@@ -1,6 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
from typing import List, Optional, Tuple
from typing import Optional
import numpy
import torch
@@ -70,7 +70,7 @@ def _check_marlin_supported(
quant_type: ScalarType,
group_size: Optional[int],
has_zp: bool,
device_capability: Optional[int] = None) -> Tuple[bool, Optional[str]]:
device_capability: Optional[int] = None) -> tuple[bool, Optional[str]]:
if device_capability is None:
capability_tuple = current_platform.get_device_capability()
@@ -143,7 +143,7 @@ def verify_marlin_supports_shape(output_size_per_partition: int,
def check_marlin_supports_shape(output_size_per_partition: int,
input_size_per_partition: int,
input_size: int, group_size: int) \
-> Tuple[bool, Optional[str]]:
-> tuple[bool, Optional[str]]:
try:
verify_marlin_supports_shape(output_size_per_partition,
input_size_per_partition, input_size,
@@ -231,16 +231,16 @@ def marlin_make_empty_zp(device: torch.device) -> torch.Tensor:
def marlin_sort_g_idx(
g_idx: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
g_idx: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
g_idx_sort_indices = torch.argsort(g_idx).to(torch.int)
return g_idx[g_idx_sort_indices], g_idx_sort_indices
def get_scale_perms():
scale_perm: List[int] = []
scale_perm: list[int] = []
for i in range(8):
scale_perm.extend([i + 8 * j for j in range(8)])
scale_perm_single: List[int] = []
scale_perm_single: list[int] = []
for i in range(4):
scale_perm_single.extend(
[2 * i + j for j in [0, 1, 8, 9, 16, 17, 24, 25]])