@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 18c1f16d86
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 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 )