Repository Issue Activity (beta)

#282 Fix typo: s3_scales should be ps3_scales in multimodal_encoder/builder.py (AttributeError)

#285 Mismatch in timm versions between vila and ps3-torch during installation

#260 How to Set Up and Run VILA , Step-by-Step Guide Request

#158 Efficient-Large-Model/VILA1.5-13b weird outputs

#276 Installation issues on Orin Nano

#270 Abnormal Inference Time and Repetitive Summary with Efficient-Large-Model/LongVILA-R1-7B on Specific Video Chunk

#277 屎山一样的代码就不要开源了，既然开源了就好好写代码

#272 Inquiry about MoE (Mixture of Experts) Training Support

#275 Support for temporal localization (fine-tuning) in NVILA

#239 Fine Tuning VILA1.5 with new dataset

#271 Implementation of Temporal Averaging for Frame Compression

#192 Dependency conflict [torch <> triton]

#269 Difference between NVILA-8B and NVILA-8B-Video Model

#241 Why finetuning NVILA-Lite-8B-stage2 needs so much memory and so slow??

#267 Freeze the ViT during the fifth stage training process of LongVILA

#265 Questions on Fine-tuning NVILA for Robotic Navigation

#119 Data preparation for Stage 4 and Stage 5 in LONGVILA

#121 create long-video QA samples

#133 Trying to run VILA on triton with triton_llm backend

#264 What is the best practice on Jetson Orin Agx?

#262 torch.OutOfMemoryError: CUDA out of memory occurred when inferring an image or a video

#255 key error: "llava_llama"

#135 ValueError: The checkpoint you are trying to load has model type `llava_llama` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

#259 Does VILA support mobile deployment for Android or iOS?

#258 Docker image No module named 'ps3'