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

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 06:47:22 +00:00
committed by GitHub
co-authored by vllmellm TJian
parent 1a6cf39dec
commit 6af03f2394
40 changed files with 331 additions and 213 deletions
@@ -8,6 +8,9 @@ from torch.nn.parameter import Parameter
from vllm import _custom_ops as ops
from vllm.logger import init_logger
from vllm.model_executor.kernels.linear import (
init_fp8_linear_kernel,
)
from vllm.model_executor.layers.attention import Attention
from vllm.model_executor.layers.linear import LinearBase, UnquantizedLinearMethod
from vllm.model_executor.layers.quantization import QuantizationMethods
@@ -17,9 +20,6 @@ from vllm.model_executor.layers.quantization.fp8 import (
Fp8KVCacheMethod,
Fp8LinearMethod,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm import (
init_fp8_linear_kernel,
)
from vllm.model_executor.layers.quantization.utils.quant_utils import (
is_layer_skipped,
kFp8DynamicTokenSym,