73 citations · 159 across the 38 of their papers we have counts for
12 papers · 1 filter
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
Learning to Hint for Reinforcement Learning
Yu Xia, Canwen Xu, Zhewei Yao +2
Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a gr…
ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback
Bohan Zhai, Canwen Xu, Yuxiong He +1
Text-to-SQL demands precise reasoning to convert natural language questions into structured queries. While large language models (LLMs) excel in many reasoning tasks, their ability…
STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning
Jaeseong Lee, seung-won hwang, Aurick Qiao +3
Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in Large language models (LLMs). Despite this reduction, the massive number…
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
Haojun Xia, Zhen Zheng, Xiaoxia Wu +10
Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing…
ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers
Zhewei Yao, Reza Yazdani Aminabadi, Stephen Youn +3
Quantization techniques are pivotal in reducing the memory and computational demands of deep neural network inference. Existing solutions, such as ZeroQuant, offer dynamic quantiza…
ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats
Xiaoxia Wu, Zhewei Yao, Yuxiong He
In the complex domain of large language models (LLMs), striking a balance between computational efficiency and maintaining model quality is a formidable challenge. Navigating the i…
Selective Guidance: Are All the Denoising Steps of Guided Diffusion Important?
Pareesa Ameneh Golnari, Zhewei Yao, Yuxiong He
This study examines the impact of optimizing the Stable Diffusion (SD) guided inference pipeline. We propose optimizing certain denoising steps by limiting the noise computation to…
ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation
Zhewei Yao, Xiaoxia Wu, Cheng Li +2
Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs). However, a systemat…
DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing
Conglong Li, Zhewei Yao, Xiaoxia Wu +4
Recent advances on deep learning models come at the price of formidable training cost. The increasing model size is one of the root causes, but another less-emphasized fact is that…
BiFeat: Supercharge GNN Training via Graph Feature Quantization
Yuxin Ma, Ping Gong, Jun Yi +4
Graph Neural Networks (GNNs) is a promising approach for applications with nonEuclidean data. However, training GNNs on large scale graphs with hundreds of millions nodes is both r…
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam
Yucheng Lu, Conglong Li, Minjia Zhang +2
1-bit gradient compression and local steps are two representative techniques that enable drastic communication reduction in distributed SGD. Their benefits, however, remain an open…