[Feature] Support online inference (#64)

Signed-off-by: Gaohan123 <gaohan19@huawei.com>
This commit is contained in:
Gao Han authored and GitHub committed 2025-11-17 14:44:10 +08:00
1 parent bf82e18374
commit c5a89302f1
52 files changed
+3666 -685

No files matched your search

+3
View File
@@ -7,6 +7,7 @@ import torch
from vllm.config import VllmConfig
from vllm.inputs import ProcessorInputs, PromptType
from vllm.inputs.parse import split_enc_dec_inputs
from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
from vllm.multimodal.inputs import MultiModalFeatureSpec
@@ -25,6 +26,8 @@ from vllm_omni.engine import (
)
from vllm_omni.inputs.preprocess import OmniInputPreprocessor
logger = init_logger(__name__)
class OmniProcessor(Processor):
@staticmethod