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, 22:15 UTC
[Bugfix] Add test example for Ultravox v0.5 (#13890)
Cyrus Leung committed
Feb 26, 2025 at 18:31 UTC
7b700ec8c8ed66c505cb9e98e8f706807ee64bbf
1 file changed
+1
tests/models/registry.py
+1
@@ -285,6 +285,7 @@ _MULTIMODAL_EXAMPLE_MODELS = {
285
"Qwen2_5_VLForConditionalGeneration": _HfExamplesInfo("Qwen/Qwen2.5-VL-3B-Instruct", # noqa: E501
286
min_transformers_version="4.49"), # noqa: E501
287
"UltravoxModel": _HfExamplesInfo("fixie-ai/ultravox-v0_4",
288
+ extras={"v0.5": "fixie-ai/ultravox-v0_5-llama-3_2-1b"}, # noqa: E501
289
trust_remote_code=True),
290
# [Encoder-decoder]
291
"MllamaForConditionalGeneration": _HfExamplesInfo("meta-llama/Llama-3.2-11B-Vision-Instruct"), # noqa: E501