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 11, 01:15 UTC
[ci] Fix Pytorch compilation test oom in 2.10 (#31194)
Signed-off-by: angelayi <yiangela7@gmail.com>
Angela Yi committed
Dec 22, 2025 at 17:56 UTC
612d5ffdab4bc48e7eae327bc5903920be528db2
1 file changed
+1
tests/compile/test_dynamic_shapes_compilation.py
+1
@@ -77,6 +77,7 @@ def test_dynamic_shapes_compilation(
77
"evaluate_guards": evaluate_guards,
78
},
79
},
80
+ max_model_len=1024,
81
)
82
83
output = model.generate(prompt)