[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:
co-authored by
vllmellm
TJian
parent
1a6cf39dec
commit
6af03f2394
@@ -8,6 +8,9 @@ from torch.nn import Module
|
||||
from torch.nn.parameter import Parameter
|
||||
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.kernels.linear import (
|
||||
init_fp8_linear_kernel,
|
||||
)
|
||||
from vllm.model_executor.layers.linear import (
|
||||
LinearBase,
|
||||
LinearMethodBase,
|
||||
@@ -18,9 +21,6 @@ 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.utils.marlin_utils_fp8 import (
|
||||
apply_fp8_marlin_linear,
|
||||
prepare_fp8_layer_for_marlin,
|
||||
|
||||
Reference in New Issue
Block a user