Related papers: LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel fo…
Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we analyze zero-point distortion in binarization and propose a…
Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have…
Deploying large language models (LLMs) on edge platforms is challenged by their high computational and memory demands. Although recent low-bit quantization methods (e.g., BitNet, DeepSeek) compress weights to as little as 1.58 bits with…
High performance dense linear algebra (DLA) libraries often rely on a general matrix multiply (Gemm) kernel that is implemented using assembly or with vector intrinsics. In particular, the real-valued Gemm kernels provide the overwhelming…
LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…
Quantization is a practical technique for making large language models easier to deploy by reducing the precision used to store and operate on model weights. This can lower memory use and improve runtime feasibility on constrained hardware,…
The quantization of large language models (LLMs) is crucial for deploying them on devices with limited computational resources. While advanced quantization algorithms offer improved performance compared to the basic linear quantization,…
Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…
Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…
The proliferation of large language models (LLMs) is accelerating the integration of multimodal assistants into edge devices, where inference is executed under stringent latency and energy constraints, often exacerbated by intermittent…
The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…
Large Language Models (LLMs) have become increasingly prominent for daily tasks, from improving sound-totext translation to generating additional frames for the latest video games. With the help of LLM inference frameworks, such as…
Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for…
Deploying large language models (LLMs) on end-user devices is gaining importance due to benefits in responsiveness, privacy, and operational cost. Yet the limited memory and compute capability of mobile and desktop GPUs make efficient…
Scalable classical simulation of quantum circuits is crucial for advancing quantum algorithm development and validating emerging hardware. This work focuses on performance enhancements through targeted low-level and NUMA-aware tuning on a…
In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…
The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression --…
Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…
This paper presents a novel network compression framework Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant…