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

[Refactor] Remove duplicate ceil_div (#20023)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2025-06-25 01:19:09 -04:00
committed by GitHub
parent 7108934142
commit 879f69bed3
7 changed files with 20 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
View File

@@ -19,7 +19,7 @@ from vllm import _custom_ops as ops
from vllm.model_executor.layers.quantization.utils.fp8_utils import (
w8a8_block_fp8_matmul,
)
from vllm.utils import FlexibleArgumentParser
from vllm.utils import FlexibleArgumentParser, cdiv
DEFAULT_MODELS = list(WEIGHT_SHAPES.keys())
DEFAULT_BATCH_SIZES = [1, 16, 32, 64, 128, 256, 512]
@@ -117,14 +117,9 @@ def bench_fp8(
scale_a = torch.tensor(1.0, device="cuda", dtype=torch.float32)
scale_b = torch.tensor(1.0, device="cuda", dtype=torch.float32)
def ceil_div(x: int, y: int) -> int:
return (x + y - 1) // y
block_scale_a = torch.rand(
(m, ceil_div(k, 128)), device="cuda", dtype=torch.float32
)
block_scale_a = torch.rand((m, cdiv(k, 128)), device="cuda", dtype=torch.float32)
block_scale_b = torch.rand(
ceil_div(k, 128), ceil_div(n, 128), device="cuda", dtype=torch.float32
cdiv(k, 128), cdiv(n, 128), device="cuda", dtype=torch.float32
)
block_scale_a_M_major = block_scale_a.t().contiguous().t()
block_scale_b_K_major = block_scale_b.t().contiguous().t()