[Mypy] Fix mypy typing for Voxtral and vision models (#58251)

Signed-off-by: Ashraf Bhuiyan <mbhuiyan@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Ashraf Bhuiyan
2026-09-28 15:52:50 -04:00
committed by GitHub
co-authored by Wentao Ye
parent 2840ca7a33
commit 2619b6b72b
5 changed files with 34 additions and 20 deletions
@@ -16,7 +16,9 @@ from vllm import LLM, SamplingParams
from vllm.assets.audio import AudioAsset
from vllm.config import CUDAGraphMode
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.protocol import StreamingInput
from vllm.platforms import current_platform
from vllm.renderers.inputs.preprocess import parse_model_prompt
from vllm.utils.math_utils import cdiv
from vllm.v1.engine.async_llm import AsyncLLM
from vllm.v1.kv_cache_interface import SlidingWindowSpec
@@ -222,6 +224,14 @@ async def test_voxtral_realtime_generator(audio_assets, tokenizer, async_engine)
sampling_params = SamplingParams(temperature=0.0, max_tokens=1)
audio_config = tokenizer.instruct_tokenizer.audio_encoder.audio_config
async def input_stream(audio_buffer):
async for prompt in audio_buffer.get_input_stream():
parsed_prompt = parse_model_prompt(async_engine.model_config, prompt)
(engine_input,) = await async_engine.renderer.render_cmpl_async(
[parsed_prompt]
)
yield StreamingInput(prompt=engine_input)
output_tokens_list = []
for i, audio_asset in enumerate(audio_assets):
output_tokens = []
@@ -241,7 +251,7 @@ async def test_voxtral_realtime_generator(audio_assets, tokenizer, async_engine)
request_id = f"session-{i}"
async for resp in async_engine.generate(
prompt=buffer.get_input_stream(),
prompt=input_stream(buffer),
sampling_params=sampling_params,
request_id=request_id,
):