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 14, 05:30 UTC
test: Remove vestigial skip for prompt embeds tests after landing v1 Prompt Embeds support (#25291)
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Andrew Sansom committed
Sep 19, 2025 at 19:33 UTC
c7e713616a53a097809609d5a7b536e8bfad4ab8
1 file changed
-3
tests/entrypoints/openai/test_completion_with_prompt_embeds.py
-3
@@ -14,9 +14,6 @@ from transformers import AutoConfig
14
15
from ...utils import RemoteOpenAIServer
16
17
-pytest.skip("Skipping prompt_embeds test until V1 supports it.",
18
- allow_module_level=True)
19
-
17
# any model with a chat template should work here
18
MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
19