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 7, 11:30 UTC
[Bugfix] Fix MM processor test for Qwen3.5 (#35797)
Signed-off-by: Roger Wang <hey@rogerw.io>
Roger Wang committed
Mar 2, 2026 at 15:05 UTC
1b82b433fca28bcf7c9f1e8053d3abab61eaa4db
1 file changed
+2
tests/models/multimodal/processing/test_common.py
+2
@@ -127,6 +127,8 @@ MM_DATA_PATCHES = {
127
"glmasr": glmasr_patch_mm_data,
128
"interns1_pro": qwen3_vl_patch_mm_data,
129
"molmo2": qwen3_vl_patch_mm_data,
130
+ "qwen3_5": qwen3_vl_patch_mm_data,
131
+ "qwen3_5_moe": qwen3_vl_patch_mm_data,
132
"qwen3_vl": qwen3_vl_patch_mm_data,
133
"qwen3_vl_moe": qwen3_vl_patch_mm_data,
134
}