23 citations · 40 across the 22 of their papers we have counts for
24 papers
BitSnap: Checkpoint Sparsification and Quantization in LLM Training
Yanxin Peng, Qingping Li, Baodong Wu +4
As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault toler…
Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
Enshu Liu, Qian Chen, Xuefei Ning +4
Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due t…
STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning
Zixiao Huang, Junhao Hu, Hao Lin +9
The rapid scaling of large language models (LLMs) has significantly increased GPU memory pressure, which is further aggravated by training optimization techniques such as virtual p…
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
Tianyu Fu, Yi Ge, Yichen You +6
Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled S…
PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
Tengxuan Liu, Shiyao Li, Jiayi Yang +7
Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT rea…
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
Zhihang Yuan, Rui Xie, Yuzhang Shang +5
Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency c…
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
Zhihang Yuan, Siyuan Wang, Rui Xie +6
In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing…
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
Hanling Zhang, Rundong Su, Zhihang Yuan +5
Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often…
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms
Yuwei Yan, Yu Shang, Qingbin Zeng +9
The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enha…
Megrez-Omni Technical Report
Boxun Li, Yadong Li, Zhiyuan Li +12
In this work, we present the Megrez models, comprising a language model (Megrez-3B-Instruct) and a multimodal model (Megrez-3B-Omni). These models are designed to deliver fast infe…
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models
Tianyu Fu, Tengxuan Liu, Qinghao Han +5
The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing to…
E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
Zhihang Yuan, Yuzhang Shang, Hanling Zhang +7
Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these m…
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
Shiyao Li, Yingchun Hu, Xuefei Ning +10
Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significa…
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
Luning Wang, Shiyao Li, Xuefei Ning +4
Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in…
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin +6
The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their subst…
Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths
Tianyu Fu, Haofeng Huang, Xuefei Ning +10
Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods ty…
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Zhihang Yuan, Hanling Zhang, Pu Lu +6
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAt…
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Tianchen Zhao, Tongcheng Fang, Haofeng Huang +10
Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, la…
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Tianchen Zhao, Xuefei Ning, Tongcheng Fang +6
Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-con…
HETHUB: A Distributed Training System with Heterogeneous Cluster for Large-Scale Models
Si Xu, Zixiao Huang, Yan Zeng +11
Training large-scale models relies on a vast number of computing resources. For example, training the GPT-4 model (1.8 trillion parameters) requires 25000 A100 GPUs . It is a chall…
A Survey on Efficient Inference for Large Language Models
Zixuan Zhou, Xuefei Ning, Ke Hong +12
Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirem…
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
Enshu Liu, Junyi Zhu, Zinan Lin +8
Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate we…
Evaluating Quantized Large Language Models
Shiyao Li, Xuefei Ning, Luning Wang +6
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumpt…
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
Tao Yuan, Xuefei Ning, Dong Zhou +10
State-of-the-art large language models (LLMs) are now claiming remarkable supported context lengths of 256k or even more. In contrast, the average context lengths of mainstream ben…