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
[CI/Build] Fix Prithvi plugin test (#27393)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Oct 23, 2025 at 15:30 UTC
bfb240cc4963b60c522c3641dcfac6ca2b50d6d0
1 file changed
+1
tests/plugins_tests/test_io_processor_plugins.py
+1
@@ -100,6 +100,7 @@ def test_prithvi_mae_plugin_offline(vllm_runner, model_name: str):
100
model_name,
101
runner="pooling",
102
skip_tokenizer_init=True,
103
+ enable_mm_embeds=True,
104
trust_remote_code=True,
105
enforce_eager=True,
106
# Limit the maximum number of parallel requests