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, 04:15 UTC
[CI/Build] Fix Bad Import In Test (#3473)
Robert Shaw committed
Mar 18, 2024 at 15:28 UTC
097aa0ea220b45d82440a8072e8e3a2ce4631fdf
1 file changed
+1
-1
tests/test_cache_block_hashing.py
+1
-1
@@ -7,7 +7,7 @@ from typing import List, Optional
7
import pytest
8
9
from vllm.lora.request import LoRARequest
10
-from vllm.transformers_utils.tokenizer import TokenizerGroup
10
+from vllm.transformers_utils.tokenizer_group import TokenizerGroup
11
from vllm.sequence import Sequence
12
13
# Make two prefixes with different first blocks.