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 17, 00:30 UTC
[Bugfix] Fix arguments passed to `Sequence` in stop checker test (#5092)
Cyrus Leung committed
May 29, 2024 at 15:16 UTC
18c1f16d86d5130ca989d32a3f05142a6652ba0d
1 file changed
+5
-2
tests/engine/output_processor/test_stop_checker.py
+5
-2
@@ -15,8 +15,11 @@ def sequence_with_eos(text: str, eos_token: str,
15
"""
16
seq = Sequence(
17
seq_id=0,
18
- prompt="",
19
- prompt_token_ids=[],
18
+ inputs={
19
+ "prompt": "",
20
+ "prompt_token_ids": [],
21
+ "multi_modal_data": None,
22
+ },
23
block_size=16,
24
eos_token_id=eos_token_id,
25
)