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 15, 12:15 UTC
[CI][TPU] Skip Multimodal test (#17488)
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
Siyuan Liu committed
Apr 30, 2025 at 19:51 UTC
dbc18e78165e72291703f6aaf991267fbbc19d2d
1 file changed
+2
tests/v1/tpu/test_multimodal.py
+2
@@ -32,6 +32,8 @@ def base64_encoded_image() -> dict[str, str]:
32
async def test_basic_vision(model_name: str, base64_encoded_image: dict[str,
33
str]):
34
35
+ pytest.skip("Skip this test until it's fixed.")
36
+
37
def whats_in_this_image_msg(b64):
38
return [{
39
"role":