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, 18:45 UTC
[CI] Fix Flaky test_eagle_max_len Test (#30306)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Micah Williamson committed
Dec 9, 2025 at 01:33 UTC
aeb82b1930454498fccc7e91f7c4e0f360cf658a
1 file changed
+1
-1
tests/v1/spec_decode/test_max_len.py
+1
-1
@@ -82,7 +82,7 @@ def test_eagle_max_len(
82
len(o.prompt_token_ids)
83
< 80
84
< len(o.prompt_token_ids) + len(o.outputs[0].token_ids)
85
- < 200
85
+ <= 200
86
), (
87
"This test is only meaningful if the output "
88
"is longer than the eagle max length"