相关论文: XFP: Quality-Targeted Adaptive Codebook Quantizati…

Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on…

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs: coarse-grained ($\textit{e.g.,}$ channel-wise) quantization…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by the…

Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a…

Quantizing the activations of large language models (LLMs) has been a significant challenge due to the presence of structured outliers. Most existing methods focus on the per-token or per-tensor quantization of activations, making it…

Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions still show limitations of either non-negligible accuracy drop or low system efficiency. In this…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Specialized edge accelerators rely on low-bit quantization, but vendor compilers differ in scaling, clipping, and kernel support, often as black boxes. The same floating-point (FP) checkpoint can therefore yield inconsistent accuracy across…

Although post-training quantization (PTQ) provides an efficient numerical compression scheme for deploying large language models (LLMs) on resource-constrained devices, the representativeness and universality of calibration data remain a…

Fine-tuning large language models (LLMs) requires significant memory, often exceeding the capacity of a single GPU. A common solution to this memory challenge is offloading compute and data from the GPU to the CPU. However, this approach is…

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Floating-point inconsistencies across compilers can undermine the reliability of numerical software. We present LLM4FP, the first framework that uses Large Language Models (LLMs) to generate floating-point programs specifically designed to…

Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency and representational capacity. While existing ultra-low-bit…

Fault-tolerant Quantum Processing Units (QPUs) promise to deliver exponential speed-ups in select computational tasks, yet their integration into modern deep learning pipelines remains unclear. In this work, we take a step towards bridging…

Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to…

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…