#
quarot
Here are 2 public repositories matching this topic...
T²Quant (T2Quant): task- and time-aware activation quantization for diffusion language models (LLaDA, Dream). Label-free calibration + exact DP precision schedule. arXiv:2610.31198
pytorch quantization model-compression efficient-inference mixed-precision post-training-quantization gptq llm-quantization quarot masked-diffusion llada diffusion-language-models dllm activation-quantization
-
Updated
Oct 24, 2026 - Python
Add this topic to your repo
To associate your repository with the quarot topic, visit your repo's landing page and select "manage topics."