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] Skip failing test (#38369)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Mar 27, 2026 at 21:25 UTC
44a6528028ad79951de08b6a7928f6c05788d00d
1 file changed
+1
tests/models/registry.py
+1
@@ -791,6 +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",
795
),
796
"FireRedASR2ForConditionalGeneration": _HfExamplesInfo(
797
"allendou/FireRedASR2-LLM-vllm",