Related papers: ML-Triton, A Multi-Level Compilation and Language …

Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping…

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs offer promise for automation, both general-purpose and…

Large Language Models (LLMs) have recently shown promise in streamlining hardware design processes by encapsulating vast amounts of domain-specific data. In addition, they allow users to interact with the design processes through natural…

Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding…

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) installed. Although high performance is expected, LLM…

NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs. We…

To achieve peak performance on modern GPUs, one must balance two frames of mind: issuing instructions to individual threads to control their behavior, while simultaneously tracking the convergence of many threads acting in concert to…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks, but serving them efficiently at scale remains a critical challenge due to their substantial computational and latency demands. While most existing…

In high-performance computing, hotspot GPU kernels are primary bottlenecks, and expert manual tuning is costly and hard to port. Large language model methods often assume kernels can be compiled and executed cheaply, which fails in large…

The rapid adoption of large language models and multimodal foundation models has made multimodal data preparation pipelines critical AI infrastructure. These pipelines interleave CPU-heavy preprocessing with accelerator-backed (GPU/NPU/TPU)…

Modern AI workloads rely heavily on optimized computing kernels for both training and inference. These AI kernels follow well-defined data-flow patterns, such as moving tiles between DRAM and SRAM and performing a sequence of computations…

LLMs are increasingly executed in edge where limited GPU memory and heterogeneous computation jointly constrain deployment which motivates model partitioning and request scheduling. In this setting, minimizing latency requires addressing…

As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy demands, raising environmental and monetary concerns. Inference dominates LLM workloads, presenting a critical challenge for…

Linear attention is an efficient attention mechanism that has recently emerged as a promising alternative to conventional softmax attention. With its ability to process tokens in linear computational complexities, linear attention, in…

Distributed attention is a fundamental problem for scaling context window for Large Language Models (LLMs). The state-of-the-art method, Ring-Attention, suffers from scalability limitations due to its excessive communication traffic. This…

To achieve high performance on modern computers, it is vital to map algorithmic parallelism to that inherent in the hardware. From an application developer's perspective, it is also important that code can be maintained in a portable manner…

Basic Linear Algebra Subprograms (BLAS) are a set of low level linear algebra kernels widely adopted by applications involved with the deep learning and scientific computing. The massive and economic computing power brought forth by the…

3D Gaussian Splatting (3DGS) has emerged as promising alternative in 3D representation. However, it still suffers from high training cost. This paper introduces LiteGS, a high performance framework that systematically optimizes the 3DGS…