[Misc] Add indirection layer for custom ops (#3913)

This commit is contained in:
Kunshang Ji
2024-04-10 20:26:07 -07:00
committed by GitHub
parent e42df7227d
commit e9da5a40c6
14 changed files with 224 additions and 32 deletions
@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional
import torch
from torch.nn.parameter import Parameter
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (
@@ -6,7 +6,7 @@ from typing import Any, Dict, List, Optional
import torch
from torch.nn.parameter import Parameter
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (
@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional
import torch
from torch.nn.parameter import Parameter
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (
@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional
import torch
from torch.nn.parameter import Parameter
from vllm._C import ops
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization.base_config import (