biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Realtime API] Adds minimal realtime API based on websockets (#33187)

Browse Source 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Patrick von Platen
2026-01-30 11:41:29 +01:00
committed by GitHub
parent 1a7894dbdf
commit 10152d2194
21 changed files with 1316 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/v1/streaming_input/test_async_llm_streaming.py
View File

@@ -7,9 +7,10 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.inputs.data import StreamingInput
from vllm.outputs import RequestOutput
from vllm.sampling_params import RequestOutputKind, SamplingParams
from vllm.v1.engine.async_llm import AsyncLLM, StreamingInput
from vllm.v1.engine.async_llm import AsyncLLM
from vllm.v1.engine.output_processor import RequestOutputCollector