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 16, 03:15 UTC
[ci] fix broken distributed-tests-4-gpus (#11937)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Jan 11, 2025 at 09:07 UTC
899136b857d510f0e19b0e21ea32b49f8aa117ed
1 file changed
+2
-1
tests/spec_decode/e2e/test_integration_dist_tp4.py
+2
-1
@@ -108,7 +108,8 @@ def test_skip_speculation(common_llm_kwargs, per_test_common_llm_kwargs,
108
109
TODO: fix it to pass without raising Error. (#5814)
110
"""
111
- with pytest.raises(openai.APIConnectionError):
111
+ with pytest.raises(
112
+ (openai.APIConnectionError, openai.InternalServerError)):
113
run_equality_correctness_test_tp(MAIN_MODEL,
114
common_llm_kwargs,
115
per_test_common_llm_kwargs,