26 citations · 38 across the 24 of their papers we have counts for
24 papers
UniSVQ: 2-bit Unified Scalar-Vector Quantization
Haoyu Wang, Haiyan Zhao, Xingyu Yu +4
Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantization (SQ) and vector quantizat…
Rethinking the Role of Efficient Attention in Hybrid Architectures
Ziqing Qiao, Yinuo Xu, Chaojun Xiao +6
Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent se…
Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
Yingfa Chen, Zhen Leng Thai, Zihan Zhou +6
Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for long-conte…
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
Yuxiang Huang, Mingye Li, Xu Han +7
The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods e…
NOSA: Native and Offloadable Sparse Attention
Yuxiang Huang, Pengjie Wang, Jicheng Han +9
Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-free KV cache offloa…
InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
Weilin Zhao, Zihan Zhou, Zhou Su +10
Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe comp…
BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens
Ao Sun, Weilin Zhao, Xu Han +4
Existing methods for training LLMs on long-sequence data, such as Tensor Parallelism and Context Parallelism, exhibit low Model FLOPs Utilization as sequence lengths and number of…
StateX: Enhancing RNN Recall via Post-training State Expansion
Xingyu Shen, Yingfa Chen, Zhen Leng Thai +3
Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token complexity when processing long contexts.…
BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
Chenyang Song, Weilin Zhao, Xu Han +5
To alleviate the computational burden of large language models (LLMs), architectures with activation sparsity, represented by mixture-of-experts (MoE), have attracted increasing at…
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
Shangzhan Li, Zefan Wang, Ye He +8
Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations thro…
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
Weilin Zhao, Tengyu Pan, Xu Han +9
Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify…
Cost-Optimal Grouped-Query Attention for Long-Context Modeling
Yingfa Chen, Yutong Wu, Chenyang Song +5
Grouped-Query Attention (GQA) is a widely adopted strategy for reducing the computational cost of attention layers in large language models (LLMs). However, current GQA configurati…
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
Jianling Li, Shangzhan Li, Zhenye Gao +9
Triton, a high-level Python-like language designed for building efficient GPU kernels, is widely adopted in deep learning frameworks due to its portability, flexibility, and access…
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
Yuxiang Huang, Mingye Li, Xu Han +7
While long-context inference is crucial for advancing large language model (LLM) applications, its prefill speed remains a significant bottleneck. Current approaches, including seq…
Densing Law of LLMs
Chaojun Xiao, Jie Cai, Weilin Zhao +7
Large Language Models (LLMs) have emerged as a milestone in artificial intelligence, and their performance can improve as the model size increases. However, this scaling brings gre…
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
Yuqi Luo, Chenyang Song, Xu Han +7
Activation sparsity denotes the existence of substantial weakly-contributed elements within activation outputs that can be eliminated, benefiting many important applications concer…
Exploring the Benefit of Activation Sparsity in Pre-training
Zhengyan Zhang, Chaojun Xiao, Qiujieli Qin +7
Pre-trained Transformers inherently possess the characteristic of sparse activation, where only a small fraction of the neurons are activated for each token. While sparse activatio…
Enabling Real-Time Conversations with Minimal Training Costs
Wang Xu, Shuo Wang, Weilin Zhao +6
Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating on…
Configurable Foundation Models: Building LLMs from a Modular Perspective
Chaojun Xiao, Zhengyan Zhang, Chenyang Song +20
Advancements in LLMs have recently unveiled challenges tied to computational efficiency and continual scalability due to their requirements of huge parameters, making the applicati…
Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts
Yingfa Chen, Chenlong Hu, Cong Feng +5
This study presents a multi-modal multi-granularity tokenizer specifically designed for analyzing ancient Chinese scripts, focusing on the Chu bamboo slip (CBS) script used during…
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
Yuan Yao, Tianyu Yu, Ao Zhang +20
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the nex…
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework
Kunlun Zhu, Yifan Luo, Dingling Xu +10
Retrieval-Augmented Generation (RAG) is a powerful approach that enables large language models (LLMs) to incorporate external knowledge. However, evaluating the effectiveness of RA…
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
Xinrong Zhang, Yingfa Chen, Shengding Hu +6
As large language models (LLMs) increasingly permeate daily lives, there is a growing demand for real-time interactions that mirror human conversations. Traditional turn-based chat…
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
Weilin Zhao, Yuxiang Huang, Xu Han +7
Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal…