6 papers · 1 filter
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Haocheng Xi, Shuo Yang, Yilong Zhao +13
Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregre…
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Jinda Jia, Jisen Li, Zhongzhu Zhou +8
KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent wor…
Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models
Minseo Kim, Coleman Hooper, Aditya Tomar +5
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generati…
Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals
Qinsi Wang, Jinghan Ke, Hancheng Ye +6
Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform…
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
Samir Khaki, Xiuyu Li, Junxian Guo +7
Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and…
Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
Qinsi Wang, Jinghan Ke, Masayoshi Tomizuka +3
We provide a new LLM-compression solution via SVD, unlocking new possibilities for LLM compression beyond quantization and pruning. We point out that the optimal use of SVD lies in…