7 papers · 1 filter
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…
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
Andrei Panferov, Erik Schultheis, Soroush Tabesh +1
The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models s…
ASIDE: Architectural Separation of Instructions and Data in Language Models
Egor Zverev, Evgenii Kortukov, Alexander Panfilov +5
Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks. In particular, previous work has…
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Roberto L. Castro, Andrei Panferov, Soroush Tabesh +5
Training large language models (LLMs) models directly in low-precision offers a way to address computational costs by improving both throughput and energy efficiency. For those pur…
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
Saleh Ashkboos, Mahdi Nikdan, Soroush Tabesh +3
Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven diffic…
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
Andrei Panferov, Jiale Chen, Soroush Tabesh +3
One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment. While post-training compres…