85 citations · 151 across the 17 of their papers we have counts for
17 papers
Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit
Xiaomi MiMo Team, Anqi Liu, Aoxin Ma +28
We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse Mixture-of-Experts (MoE), and…
T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup
Jianyu Wei, Qingtao Li, Shijie Cao +5
Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) i…
TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Zhirui Huang, Rui Ma, Shijie Cao +5
Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference…
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache
Dayou Du, Shijie Cao, Jianyi Cheng +3
The growth of long-context Large Language Models (LLMs) significantly increases memory and bandwidth pressure during autoregressive decoding due to the expanding Key-Value (KV) cac…
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
Jinheng Wang, Hansong Zhou, Ting Song +7
The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient…
Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models
Xin Ding, Shijie Cao, Ting Cao +1
Vision generative models have recently made significant advancements along two primary paradigms: diffusion-style and language-style, both of which have demonstrated excellent scal…
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
Yizhao Gao, Zhichen Zeng, Dayou Du +8
Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A prom…
LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference
Zhiwen Mo, Lei Wang, Jianyu Wei +8
Large Language Model (LLM) inference becomes resource-intensive, prompting a shift toward low-bit model weights to reduce the memory footprint and improve efficiency. Such low-bit…
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge
Jianyu Wei, Shijie Cao, Ting Cao +4
The deployment of Large Language Models (LLMs) on edge devices is increasingly important to enhance on-device intelligence. Weight quantization is crucial for reducing the memory f…
BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
Dayou Du, Yijia Zhang, Shijie Cao +4
The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantizati…
AFPQ: Asymmetric Floating Point Quantization for LLMs
Yijia Zhang, Sicheng Zhang, Shijie Cao +4
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can sav…
Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference
Ranggi Hwang, Jianyu Wei, Shijie Cao +4
Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high…
Adam Accumulation to Reduce Memory Footprints of both Activations and Gradients for Large-scale DNN Training
Yijia Zhang, Yibo Han, Shijie Cao +5
Running out of GPU memory has become a main bottleneck for large-scale DNN training. How to reduce the memory footprint during training has received intensive research attention. W…
Accurate and Structured Pruning for Efficient Automatic Speech Recognition
Huiqiang Jiang, Li Lyna Zhang, Yuang Li +7
Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model s…
Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models
Yijia Zhang, Lingran Zhao, Shijie Cao +6
Efficient deployment of large language models (LLMs) necessitates low-bit quantization to minimize model size and inference cost. While low-bit integer formats (e.g., INT8/INT4) ha…
EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate
Xiaonan Nie, Xupeng Miao, Shijie Cao +7
Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i…
Balanced Sparsity for Efficient DNN Inference on GPU
Zhuliang Yao, Shijie Cao, Wencong Xiao +2
In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical…