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 8, 11:15 UTC
Don't try and run GLM-ASR with remote code (#34352)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Feb 11, 2026 at 17:09 UTC
67a42b5a44fe196250142f1e8ddee44d7061500f
1 file changed
-1
tests/models/registry.py
-1
@@ -725,7 +725,6 @@ _MULTIMODAL_EXAMPLE_MODELS = {
725
"Gemma3nForConditionalGeneration": _HfExamplesInfo("google/gemma-3n-E2B-it"),
726
"GlmAsrForConditionalGeneration": _HfExamplesInfo(
727
"zai-org/GLM-ASR-Nano-2512",
728
- trust_remote_code=True,
728
min_transformers_version="5.0.0",
729
),
730
"GraniteVision": _HfExamplesInfo("ibm-granite/granite-vision-3.3-2b"),