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 1, 21:15 UTC
[Bugfix] Update mistral tokenizer test for continue_final_message fix (#44622)
Signed-off-by: Xu Zhou <xuzhou9417@163.com> Co-authored-by: Xu Zhou <xuzhou9417@163.com>
XuZhou committed
Jun 5, 2026 at 16:13 UTC
d61d8566ec30691645d91727ca7daced073e8f14
1 file changed
+2
-2
tests/tokenizers_/test_mistral.py
+2
-2
@@ -797,11 +797,11 @@ class TestMistralTokenizer:
797
True,
798
(
799
[1, 3, 23325, 2294, 1686, 4, 23325],
800
- [1, 3, 22177, 4304, 2662, 4, 22177, 2],
800
+ [1, 3, 22177, 4304, 2662, 4, 22177],
801
),
802
(
803
"<s>[INST]▁Hello▁world▁![/INST]▁Hello",
804
- ("<s>[INST]Hello world ![/INST]Hello</s>"),
804
+ "<s>[INST]Hello world ![/INST]Hello",
805
),
806
),
807
],