SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Paper • 2509.22944 • Published • 80
Model Card for Model ID
This is prototype for SINQ (https://arxiv.org/abs/2509.22944). It is in progress at: https://github.com/pytorch/ao/pull/3156.
E2E support is comming soon!
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support