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 6, 20:30 UTC
[CI Failure] Fix Language Models Test (Extended Pooling) daily CI Failure (#36761)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
wang.yuqi committed
Mar 12, 2026 at 12:22 UTC
6ecabe493628eeeafc346dbe2ee3b6c0a6d94a80
1 file changed
+2
-1
tests/models/language/pooling/test_mm_classifier_conversion.py
+2
-1
@@ -32,7 +32,8 @@ def test_idefics_multimodal(
32
33
34
def update_config(config):
35
- config.text_config.update(
35
+ text_config = config.get_text_config()
36
+ text_config.update(
37
{
38
"architectures": ["Gemma3ForSequenceClassification"],
39
"classifier_from_token": ["A", "B", "C", "D", "E"],