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

[Refactor] [1/N] Reorganize kernel abstraction directory (#34055)

Browse Source 
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
This commit is contained in:
BadrBasowid
2026-02-24 14:47:22 +08:00
committed by GitHub
parent 1a6cf39dec
commit 6af03f2394
40 changed files with 331 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/kernels/quantization/test_scaled_mm_kernel_selection.py
View File

@@ -10,16 +10,10 @@ from abc import ABC
import pytest
from vllm.model_executor.layers.quantization.kernels.scaled_mm import (
Int8ScaledMMLinearLayerConfig,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm.aiter import (
from vllm.model_executor.kernels.linear import (
AiterInt8ScaledMMLinearKernel,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm.cpu import (
CPUInt8ScaledMMLinearKernel,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm.ScaledMMLinearKernel import ( # noqa: E501
Int8ScaledMMLinearLayerConfig,
ScaledMMLinearKernel,
)