rebase: adapt to vLLM v0.29 APIs

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-09-10 00:41:52 +08:00
1 parent 6a63f5cb99
commit 87a1fd8da2
60 files changed
+2038 -514

No files matched your search

@@ -17,7 +17,7 @@ from transformers.generation.configuration_utils import GenerationConfig
from transformers.generation.utils import ALL_CACHE_NAMES, GenerationMixin
from transformers.utils.generic import ModelOutput
from vllm.config.vllm import get_current_vllm_config
from vllm.model_executor.models.utils import AutoWeightsLoader, WeightsMapper
from vllm.model_executor.models.utils import WeightsMapper
from vllm.transformers_utils.config import get_config
from vllm_omni.diffusion.data import DiffusionOutput, OmniDiffusionConfig
@@ -33,6 +33,7 @@ from vllm_omni.diffusion.request import OmniDiffusionRequest
from vllm_omni.diffusion.worker.request_batch import DiffusionRequestBatch
from vllm_omni.inputs.data import OmniTextPrompt
from vllm_omni.model_executor.models.hunyuan_image3.siglip2 import Siglip2VisionTransformer
from vllm_omni.model_executor.models.weight_loader import AutoWeightsLoader
from . import request_layout as request_layout_utils
from .hunyuan_image3_tokenizer import TokenizerEncodeOutput, TokenizerWrapper
@@ -24,7 +24,7 @@ from vllm.distributed import (
tensor_model_parallel_all_reduce,
)
from vllm.logger import init_logger
from vllm.model_executor.layers.batch_invariant import linear_batch_invariant
from vllm.model_executor.determinism.batch_invariant import linear_batch_invariant
from vllm.model_executor.layers.linear import (
ColumnParallelLinear,
QKVParallelLinear,