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 15, 03:30 UTC
[Minor] Clean up incorrect comment in test (#20382)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Jul 2, 2025 at 17:13 UTC
d265414dbc9f819ee8f20a69f735a4bf0a667680
1 file changed
-3
tests/engine/test_options.py
-3
@@ -48,9 +48,6 @@ def test_enable_prompt_embeds(hf_runner, model: str,
48
ctx = (nullcontext() if enable_prompt_embeds else pytest.raises(
49
ValueError, match="set `--enable-prompt-embeds`"))
50
51
- # This test checks if the flag skip_tokenizer_init skips the initialization
52
- # of tokenizer and detokenizer. The generated output is expected to contain
53
- # token ids.
51
llm = LLM(
52
model=model,
53
enable_prompt_embeds=enable_prompt_embeds,