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 3, 04:15 UTC
[Test] Replace zephyr-7b-beta (7B) with SmolLM2-135M in tokenization test (#43085)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Kevin H. Luu committed
May 21, 2026 at 01:57 UTC
ebbfb34e3e058bd539db9e5015d0c18b7ce5a5e0
1 file changed
+1
-1
tests/entrypoints/serve/tokenize/test_tokenization.py
+1
-1
@@ -9,7 +9,7 @@ from tests.utils import RemoteOpenAIServer
9
from vllm.tokenizers import get_tokenizer
10
11
# any model with a chat template should work here
12
-MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
12
+MODEL_NAME = "HuggingFaceTB/SmolLM2-135M-Instruct"
13
14
15
@pytest.fixture(scope="module")