Dan Alistarh

8

Papers

6

Total Citations

Papers (8)

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence

Layer-wise Quantization for Quantized Optimistic Dual Averaging

The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation

SPADE: Sparsity-Guided Debugging for Deep Neural Networks

Error Feedback Can Accurately Compress Preconditioners

Extreme Compression of Large Language Models via Additive Quantization