@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 097aa0ea22
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, 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.