[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
@@ -13,6 +13,9 @@ from vllm import _custom_ops as ops
|
||||
from vllm._aiter_ops import rocm_aiter_ops
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
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.batch_invariant import (
|
||||
vllm_is_batch_invariant,
|
||||
@@ -46,9 +49,6 @@ 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_utils import (
|
||||
apply_fi_trtllm_fp8_per_tensor_moe,
|
||||
|
||||
Reference in New Issue
Block a user