@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d18bab3587
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 16, 22:00 UTC

[CI] Fix base url doesn't strip "/" (#6087)

SangBin Cho committed Jul 3, 2024 at 13:31 UTC d18bab3587e6804aaa74f93fb1d55ab5766f75a3
1 file changed +1 -1
tests/entrypoints/openai/test_completion.py
+1 -1
@@ -606,7 +606,7 @@ async def test_guided_decoding_type_error(client: openai.AsyncOpenAI,
606 [MODEL_NAME],
607 )
608 async def test_tokenize(client: openai.AsyncOpenAI, model_name: str):
609 - base_url = str(client.base_url)[:-3]
609 + base_url = str(client.base_url)[:-3].strip("/")
610 tokenizer = get_tokenizer(tokenizer_name=MODEL_NAME, tokenizer_mode="fast")
611
612 for add_special in [False, True]: