908 citations · 2.4k across the 149 of their papers we have counts for
24 papers · 1 filter
LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs
Erik Schultheis, Dan Alistarh
We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are charact…
Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks
Sergey Pankratov, Dan Alistarh
Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simult…
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
Jiale Chen, Vage Egiazarian, Roberto L. Castro +2
Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization er…
Beyond Outliers: A Study of Optimizers Under Quantization
Georgios Vlassis, Saleh Ashkboos, Alexandra Volkova +2
As new optimizers gain traction and model quantization becomes standard for efficient deployment, a key question arises: how does the choice of optimizer affect model performance i…
CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
Soroush Tabesh, Mher Safaryan, Andrei Panferov +2
Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAG…
Expand Neurons, Not Parameters
Linghao Kong, Inimai Subramanian, Yonadav Shavit +3
This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance. We show that this gain cor…