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 5, 21:00 UTC
[CI] Fix Ernie4.5-VL initialization test (#38429)
Signed-off-by: haosdent <haosdent@gmail.com>
haosdent committed
Mar 28, 2026 at 22:43 UTC
b2bc736b1247a76e6ab1cfbe38ae39c3c307de40
1 file changed
+1
-1
tests/models/registry.py
+1
-1
@@ -791,7 +791,7 @@ _MULTIMODAL_EXAMPLE_MODELS = {
791
"Ernie4_5_VLMoeForConditionalGeneration": _HfExamplesInfo(
792
"baidu/ERNIE-4.5-VL-28B-A3B-PT",
793
trust_remote_code=True,
794
- revision="refs/pr/14",
794
+ revision="refs/pr/17",
795
),
796
"FireRedASR2ForConditionalGeneration": _HfExamplesInfo(
797
"allendou/FireRedASR2-LLM-vllm",