@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 899136b857
Fork 0

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,