Signed-off-by: Rein Yang <ruiruyang2@gmail.com> Co-authored-by: Rein <rein@Reins-MacBook-Air.local>
30 lines
1.6 KiB
Python
30 lines
1.6 KiB
Python
import sys
|
|
|
|
from vllm.inputs.data import TokensPrompt as _OriginalTokensPrompt
|
|
from vllm.model_executor.layers.rotary_embedding import (
|
|
MRotaryEmbedding as _OriginalMRotaryEmbedding,
|
|
)
|
|
from vllm.v1.engine import EngineCoreOutput as _OriginalEngineCoreOutput
|
|
from vllm.v1.engine import EngineCoreOutputs as _OriginalEngineCoreOutputs
|
|
from vllm.v1.engine import EngineCoreRequest as _OriginalEngineCoreRequest
|
|
from vllm.v1.request import Request as _OriginalRequest
|
|
|
|
from vllm_omni.engine import OmniEngineCoreOutput, OmniEngineCoreOutputs, OmniEngineCoreRequest
|
|
from vllm_omni.inputs.data import OmniTokensPrompt
|
|
from vllm_omni.model_executor.layers.mrope import MRotaryEmbedding
|
|
from vllm_omni.request import OmniRequest
|
|
|
|
for module_name, module in sys.modules.items():
|
|
if hasattr(module, "EngineCoreOutput") and module.EngineCoreOutput == _OriginalEngineCoreOutput:
|
|
module.EngineCoreOutput = OmniEngineCoreOutput
|
|
if hasattr(module, "EngineCoreOutputs") and module.EngineCoreOutputs == _OriginalEngineCoreOutputs:
|
|
module.EngineCoreOutputs = OmniEngineCoreOutputs
|
|
if hasattr(module, "TokensPrompt") and module.TokensPrompt == _OriginalTokensPrompt:
|
|
module.TokensPrompt = OmniTokensPrompt
|
|
if hasattr(module, "MRotaryEmbedding") and module.MRotaryEmbedding == _OriginalMRotaryEmbedding:
|
|
module.MRotaryEmbedding = MRotaryEmbedding
|
|
if hasattr(module, "Request") and module.Request == _OriginalRequest:
|
|
module.Request = OmniRequest
|
|
if hasattr(module, "EngineCoreRequest") and module.EngineCoreRequest == _OriginalEngineCoreRequest:
|
|
module.EngineCoreRequest = OmniEngineCoreRequest
|