[Model] Use explicit types in get_generation_prompt (#33551)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-02 12:38:49 +00:00
committed by GitHub
parent b398e5c819
commit b10d05b8a8
8 changed files with 82 additions and 66 deletions
+7 -7
View File
@@ -2,7 +2,7 @@
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Iterable, Mapping, Sequence
from typing import Annotated, Any, Literal, TypeAlias, cast
from typing import Annotated, Any, Literal, TypeAlias
import numpy as np
import torch
@@ -14,7 +14,7 @@ from transformers.models.whisper import WhisperFeatureExtractor
from vllm.config import ModelConfig, SpeechToTextConfig, VllmConfig
from vllm.config.multimodal import BaseDummyOptions
from vllm.distributed.parallel_state import get_tensor_model_parallel_world_size
from vllm.inputs.data import PromptType
from vllm.inputs.data import PromptType, TokensPrompt
from vllm.model_executor.layers.activation import get_act_fn
from vllm.model_executor.layers.attention import MMEncoderAttention
from vllm.model_executor.layers.linear import (
@@ -1159,8 +1159,8 @@ class GlmAsrForConditionalGeneration(
)
prompt_token_ids = tokenizer.encode(prompt)
prompt_dict = {
"prompt_token_ids": prompt_token_ids,
"multi_modal_data": {"audio": audio},
}
return cast(PromptType, prompt_dict)
return TokensPrompt(
prompt_token_ids=prompt_token_ids,
multi_modal_data={"audio": audio},
)