[V1] TPU - CI/CD use smaller model (#15054)

Signed-off-by: Alexander Matveev <amatveev@redhat.com>
This commit is contained in:
Alexander Matveev
2025-03-18 17:39:21 -04:00
committed by GitHub
parent 99abb8b650
commit 72a8639b68
2 changed files with 13 additions and 12 deletions

View File

@@ -15,9 +15,10 @@ if TYPE_CHECKING:
from tests.conftest import VllmRunner
MODELS = [
"Qwen/Qwen2.5-1.5B-Instruct",
# TODO: Enable this models with v6e
# "Qwen/Qwen2-7B-Instruct",
"meta-llama/Llama-3.1-8B",
# TODO: Add models here as necessary
# "meta-llama/Llama-3.1-8B",
]
TENSOR_PARALLEL_SIZES = [1]