Search Results for author:
Found 4 papers, 4 papers with code
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
In this work, we question the use of STE for extreme LLM compression, showing that it can be sub-optimal, and perform a systematic study of quantization-aware fine-tuning strategies for LLMs.
Fast Inference of Mixture-of-Experts Language Models with Offloading
In this work, we study the problem of running large MoE language models on consumer hardware with limited accelerator memory.
Distributed Deep Learning in Open Collaborations
Modern deep learning applications require increasingly more compute to train state-of-the-art models.
Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
Our main contribution is PRODIGE: a method that learns a weighted graph representation of data end-to-end by gradient descent.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
