[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
@@ -9,6 +9,9 @@ from torch.nn.parameter import Parameter
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
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.fused_moe.activation import MoEActivation
from vllm.model_executor.layers.fused_moe.config import (
@@ -45,9 +48,6 @@ from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig,
QuantizeMethodBase,
)
from vllm.model_executor.layers.quantization.kernels.scaled_mm import (
init_fp8_linear_kernel,
)
from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
from vllm.model_executor.layers.quantization.utils.flashinfer_fp4_moe import (
flashinfer_trtllm_fp4_moe,