A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 08:30 UTC
[Bugfix] Revert test_tokenization.py (#29729)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Nov 30, 2025 at 00:35 UTC
b9d0504a366b667f8160174af1251bf8da9f006e
1 file changed
+1
-1
tests/entrypoints/openai/test_tokenization.py
+1
-1
@@ -10,7 +10,7 @@ from vllm.transformers_utils.tokenizer import get_tokenizer
10
from ...utils import RemoteOpenAIServer
11
12
# any model with a chat template should work here
13
-MODEL_NAME = "Qwen/Qwen3-0.6B"
13
+MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
14
15
16
@pytest.fixture(scope="module")