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

6
tests/utils.py
View File

@@ -42,11 +42,9 @@ from vllm.distributed import (
)
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.entrypoints.cli.serve import ServeSubcommand
from vllm.model_executor.layers.quantization.kernels.scaled_mm import (
init_fp8_linear_kernel,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm.ScaledMMLinearKernel import ( # noqa: E501
from vllm.model_executor.kernels.linear import (
FP8ScaledMMLinearKernel,
init_fp8_linear_kernel,
)
from vllm.model_executor.layers.quantization.utils.fp8_utils import W8A8BlockFp8LinearOp
from vllm.model_executor.layers.quantization.utils.quant_utils import (