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 15, 01:00 UTC
Fix a couple of Voxtral tests (#21218)
Signed-off-by: Huy Do <huydhn@gmail.com>
Huy Do committed
Jul 19, 2025 at 02:13 UTC
cf8cc32674f30cc091b551ceb4decd79718ac9e5
1 file changed
+5
-1
tests/models/registry.py
+5
-1
@@ -449,7 +449,11 @@ _MULTIMODAL_EXAMPLE_MODELS = {
449
tokenizer="Isotr0py/Florence-2-tokenizer", # noqa: E501
450
trust_remote_code=True), # noqa: E501
451
"MllamaForConditionalGeneration": _HfExamplesInfo("meta-llama/Llama-3.2-11B-Vision-Instruct"), # noqa: E501
452
- "VoxtralForConditionalGeneration": _HfExamplesInfo("mistralai/Voxtral-Mini-3B-2507", tokenizer_mode="mistral"), # noqa: E501
452
+ "VoxtralForConditionalGeneration": _HfExamplesInfo(
453
+ "mistralai/Voxtral-Mini-3B-2507",
454
+ tokenizer_mode="mistral",
455
+ min_transformers_version="4.54"
456
+ ),
457
"WhisperForConditionalGeneration": _HfExamplesInfo("openai/whisper-large-v3"), # noqa: E501
458
459
# [Cross-encoder]