SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the sequence length increases, which has become a bottleneck for the application of LLMs on long sequences. Existing KV cache compression methods include eviction, merging, or quantization of the KV cache to reduce its size. However, compression results in irreversible information forgetting, potentially affecting the accuracy of subsequent decoding. In this paper, we propose SpeCache, which takes full advantage of the large and easily expandable CPU memory to offload the complete KV cache, and dynamically fetches KV pairs back in each decoding step based on their importance measured by low-bit KV cache copy in VRAM. To avoid inference latency caused by CPU-GPU communication, SpeCache speculatively predicts the KV pairs that the next token might attend to, allowing us to prefetch them before the next decoding step which enables parallelization of prefetching and computation. Experiments on LongBench and Needle-in-a-Haystack benchmarks verify that SpeCache effectively reduces VRAM usage while avoiding information forgetting for long sequences without re-training, even with a 10x high KV cache compression ratio.

Mixture of Lookup Experts

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects the experts, all the experts need to be loaded into VRAM. Their large parameter size still limits deployment, and offloading, which load experts into VRAM only when needed, significantly increase inference latency. To address this, we propose Mixture of Lookup Experts (MoLE), a new MoE architecture that is efficient in both communication and VRAM usage. In MoLE, the experts are Feed-Forward Networks (FFNs) during training, taking the output of the embedding layer as input. Before inference, these experts can be re-parameterized as lookup tables (LUTs) that retrieves expert outputs based on input ids, and offloaded to storage devices. Therefore, we do not need to perform expert computations during inference. Instead, we directly retrieve the expert's computation results based on input ids and load them into VRAM, and thus the resulting communication overhead is negligible. Experiments show that, with the same FLOPs and VRAM usage, MoLE achieves inference speeds comparable to dense models and significantly faster than MoE with experts offloading, while maintaining performance on par with MoE.

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet models, DiT is purely composed of a stack of transformer blocks, which renders DiT excellent in scalability like large language models. However, the growing model size and multi-step sampling paradigm bring about considerable pressure on deployment and inference. In this work, we propose a post-training quantization framework tailored for Diffusion Transforms to tackle these challenges. We firstly locate that the quantization difficulty of DiT mainly originates from the time-dependent channel-specific outliers. We propose a timestep-aware shift-and-scale strategy to smooth the activation distribution to reduce the quantization error. Secondly, based on the observation that activations of adjacent timesteps have similar distributions, we utilize a hierarchical clustering scheme to divide the denoising timesteps into multiple groups. We further design a re-parameterization scheme which absorbs the quantization parameters into nearby module to avoid redundant computations. Comprehensive experiments demonstrate that out PTQ method successfully quantize the Diffusion Transformer into 8-bit weight and 8-bit activation (W8A8) with state-of-the-art FiD score. And our method can further quantize DiT model into 4-bit weight and 8-bit activation (W4A8) without sacrificing generation quality.

Rethinking Video Tokenization: A Conditioned Diffusion-based Approach

Video tokenizers, which transform videos into compact latent representations, are key to video generation. Existing video tokenizers are based on the VAE architecture and follow a paradigm where an encoder compresses videos into compact latents, and a deterministic decoder reconstructs the original videos from these latents. In this paper, we propose a novel \underline{\textbf{C}}onditioned \underline{\textbf{D}}iffusion-based video \underline{\textbf{T}}okenizer entitled \textbf{\ourmethod}, which departs from previous methods by replacing the deterministic decoder with a 3D causal diffusion model. The reverse diffusion generative process of the decoder is conditioned on the latent representations derived via the encoder. With a feature caching and sampling acceleration, the framework efficiently reconstructs high-fidelity videos of arbitrary lengths. Results show that {\ourmethod} achieves state-of-the-art performance in video reconstruction tasks using just a single-step sampling. Even a smaller version of {\ourmethod} still achieves reconstruction results on par with the top two baselines. Furthermore, the latent video generation model trained using {\ourmethod} also shows superior performance.

GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video

The rapid advancement of video generation models has made it increasingly challenging to distinguish AI-generated videos from real ones. This issue underscores the urgent need for effective AI-generated video detectors to prevent the dissemination of false information through such videos. However, the development of high-performance generative video detectors is currently impeded by the lack of large-scale, high-quality datasets specifically designed for generative video detection. To this end, we introduce GenVidBench, a challenging AI-generated video detection dataset with several key advantages: 1) Cross Source and Cross Generator: The cross-generation source mitigates the interference of video content on the detection. The cross-generator ensures diversity in video attributes between the training and test sets, preventing them from being overly similar. 2) State-of-the-Art Video Generators: The dataset includes videos from 8 state-of-the-art AI video generators, ensuring that it covers the latest advancements in the field of video generation. 3) Rich Semantics: The videos in GenVidBench are analyzed from multiple dimensions and classified into various semantic categories based on their content. This classification ensures that the dataset is not only large but also diverse, aiding in the development of more generalized and effective detection models. We conduct a comprehensive evaluation of different advanced video generators and present a challenging setting. Additionally, we present rich experimental results including advanced video classification models as baselines. With the GenVidBench, researchers can efficiently develop and evaluate AI-generated video detection models. Datasets and code are available at https://genvidbench.github.io.

Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

Multimodal vision language models (VLMs) have made significant progress with the support of continuously increasing model sizes and data volumes. Running VLMs on edge devices has become a challenge for their widespread application. There are several efficient VLM efforts, but they often sacrifice linguistic capabilities to enhance multimodal abilities, or require extensive training. To address this quandary,we introduce the innovative framework of Efficient Vision Language Models with Elastic Visual Experts (Eve). By strategically incorporating adaptable visual expertise at multiple stages of training, Eve strikes a balance between preserving linguistic abilities and augmenting multimodal capabilities. This balanced approach results in a versatile model with only 1.8B parameters that delivers significant improvements in both multimodal and linguistic tasks. Notably, in configurations below 3B parameters, Eve distinctly outperforms in language benchmarks and achieves state-of-the-art results 68.87% in VLM Benchmarks. Additionally, its multimodal accuracy outstrips that of the larger 7B LLaVA-1.5 model.

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

Large Language Models (LLMs) have shown remarkable abilities across various language tasks, but solving complex reasoning problems remains a challenge. While existing methods like Chain-of-Thought (CoT) and Tree-of-Thought (ToT) enhance reasoning by decomposing problems or structuring prompts, they typically perform a single pass of reasoning and may fail to revisit flawed paths, compromising accuracy. To address this, we propose a novel reasoning framework called Forest-of-Thought (FoT), which integrates multiple reasoning trees to leverage collective decision-making for solving complex logical problems. FoT utilizes sparse activation strategies to select the most relevant reasoning paths, improving both efficiency and accuracy. Additionally, we introduce a dynamic self-correction strategy that enables real-time error correction and learning from past mistakes, as well as consensus-guided decision making strategies to optimize correctness and computational resources. Experimental results demonstrate that the FoT framework, combined with these strategies, significantly enhances the reasoning capabilities of LLMs, enabling them to solve complex tasks with greater precision and efficiency.

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, collecting high-quality and diverse data is both expensive and time-consuming. To mitigate this issue, we propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets through multi-agent collaboration and assessment. The framework adopts a three-pronged strategy. It initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. Subsequently, the generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality. Finaly, the above process evolves in a dynamic refinement phase, where more effective LLMs are prioritized, enhancing the overall data quality. Our empirical studies, including instruction tuning experiments with models such as Pythia and LLaMA, demonstrate the effectiveness of the proposed framework. Optimized datasets have achieved substantial improvements, with an average increase of 12% and notable gains in specific metrics, such as a 40% improvement in Fermi, as evidenced by benchmarks like MT-bench, Vicuna bench, and WizardLM testset.

MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance. In this work, we present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. We eliminate nearly all the computations of the transformer model except for the necessary computation required by the multi-head attention operation. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. Specifically, we first construct a group of in-memory lookup tables that store a large amount of discrete vectors to replace the weight matrix used in linear projection. We then use a hash algorithm to retrieve a correlated subset of vectors dynamically based on the input embedding. The retrieved vectors combined together will form the output embedding, which provides an estimation of the result of matrix multiplication operation in a fully-connected layer. Compared to conducting matrix multiplication, retrieving data blocks from memory is a much cheaper operation which requires little computations. We train MemoryFormer from scratch and conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model.

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs

Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While training-based video-LLMs deliver high performance, they often require substantial resources for training and inference. Conversely, training-free approaches offer a more efficient alternative by adapting pre-trained image-LLMs models for video tasks without additional training, but they face inference efficiency bottlenecks due to the large number of visual tokens generated from video frames. In this work, we present a novel prompt-guided visual perception framework (abbreviated as \emph{Free Video-LLM}) for efficient inference of training-free video LLMs. The proposed framework decouples spatial-temporal dimension and performs temporal frame sampling and spatial RoI cropping respectively based on task-specific prompts. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks. Extensive experiments demonstrate that our approach achieves competitive results with significantly fewer tokens, offering an optimal trade-off between accuracy and computational efficiency compared to state-of-the-art video LLMs. The code will be available at \url{https://github.com/contrastive/FreeVideoLLM}.