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

Update deprecated Python 3.8 typing (#13971)

Browse Source
This commit is contained in:
Harry Mellor
2025-03-03 01:34:51 +00:00
committed by GitHub
parent bf33700ecd
commit cf069aa8aa
300 changed files with 2294 additions and 2347 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
benchmarks/kernels/benchmark_marlin.py
View File

@@ -1,7 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
from typing import List
import torch
import torch.utils.benchmark as benchmark
from benchmark_shapes import WEIGHT_SHAPES
@@ -31,7 +29,7 @@ ACT_ORDER_OPTS = [False, True]
K_FULL_OPTS = [False, True]
def bench_run(results: List[benchmark.Measurement], model: str,
def bench_run(results: list[benchmark.Measurement], model: str,
act_order: bool, is_k_full: bool, quant_type: ScalarType,
group_size: int, size_m: int, size_k: int, size_n: int):
label = "Quant Matmul"
@@ -221,7 +219,7 @@ def main(args):
for i, model in enumerate(args.models):
print(f"[{i}] {model}")
results: List[benchmark.Measurement] = []
results: list[benchmark.Measurement] = []
for model in args.models:
for layer in WEIGHT_SHAPES[model]: