Search Results for author:
Found 7 papers, 4 papers with code
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
Second, QuIP# uses vector quantization techniques to take advantage of the ball-shaped sub-Gaussian distribution that incoherent weights possess: specifically, we introduce a set of hardware-efficient codebooks based on the highly symmetric $E_8$ lattice, which achieves the optimal 8-dimension unit ball packing.
QuIP: 2-Bit Quantization of Large Language Models With Guarantees
This work studies post-training parameter quantization in large language models (LLMs).
Performance optimizations on deep noise suppression models
We study the role of magnitude structured pruning as an architecture search to speed up the inference time of a deep noise suppression (DNS) model.
Model Preserving Compression for Neural Networks
After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands.
How Low Can We Go: Trading Memory for Error in Low-Precision Training
Low-precision arithmetic trains deep learning models using less energy, less memory and less time.
Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum
We construct a statistical diagnostic test for convergence to the stationary phase using the inner product between successive gradients and demonstrate that the proposed diagnostic works well.
Convergence diagnostics for stochastic gradient descent with constant step size
During the transient phase the procedure converges towards a region of interest, and during the stationary phase the procedure oscillates in that region, commonly around a single point.
