mirror of
https://github.com/bentoml/OpenLLM.git
synced 2026-05-04 05:42:44 -04:00
820b4991fa
This is to help with working on CPU machine Signed-off-by: aarnphm-ec2-dev <29749331+aarnphm@users.noreply.github.com>
10 lines
530 B
Python
Generated
10 lines
530 B
Python
Generated
from typing import Dict
|
|
from typing import List
|
|
|
|
import torch
|
|
|
|
def copy_blocks(arg0: List[torch.Tensor], arg1: List[torch.Tensor], arg2: Dict[int,List[int]]) -> None: ...
|
|
def gather_cached_kv(arg0: torch.Tensor, arg1: torch.Tensor, arg2: torch.Tensor, arg3: torch.Tensor, arg4: torch.Tensor) -> None: ...
|
|
def reshape_and_cache(arg0: torch.Tensor, arg1: torch.Tensor, arg2: torch.Tensor, arg3: torch.Tensor, arg4: torch.Tensor) -> None: ...
|
|
def swap_blocks(arg0: torch.Tensor, arg1: torch.Tensor, arg2: Dict[int,int]) -> None: ...
|