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, 02:15 UTC
[TPU][Bugfix] disable phi-3 test (#20632)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
QiliangCui committed
Jul 8, 2025 at 16:14 UTC
d8ee5a2ca4c73f2ce5fdc386ce5b4ef3b6e6ae70
1 file changed
+1
tests/v1/tpu/test_basic.py
+1
@@ -67,6 +67,7 @@ def test_basic(
67
assert "1024" in output or "0, 1" in output
68
69
70
+@pytest.mark.skip(reason="Temporarily disabled due to timeout")
71
@pytest.mark.skipif(not current_platform.is_tpu(),
72
reason="This is a basic test for TPU only")
73
@pytest.mark.parametrize("max_tokens", [8])