Official implementation of Prism-MoE, an efficient dense-to-MoE conversion framework for visual autoregressive generation. ICML 2026 Poster.
-
Updated
Jul 3, 2026 - Python
#
visual-autoregressive-model
Here are 3 public repositories matching this topic...
W4A4 and INT8 KV-cache quantization for Infinity VAR models. Optimized for high-fidelity generative AI deployment on edge GPUs (e.g. NVIDIA Jetson).
computer-vision pytorch gpu-acceleration quantization model-compression nvidia-jetson inference-optimization edge-ai on-device-ml weight-quantization post-training-quantization autoregressive-models generative-ai kv-cache-quantization activation-quantization visual-autoregressive-model svdquant infinity-var
-
Updated
Jun 11, 2026 - Python
Research code for the Dynamic Mixture-of-Experts in Visual Autoregressive Models paper.
sparsity transformers image-generation dynamic-routing efficient-inference mixture-of-experts autoregressive-generation visual-autoregressive-model
-
Updated
Mar 19, 2026 - Python
Add this topic to your repo
To associate your repository with the visual-autoregressive-model topic, visit your repo's landing page and select "manage topics."