Lingxiao Ma

Hongyu Wang, Shuming Ma, Li Dong et al. · microsoft-research

The increasing size of large language models has posed challenges for deployment and raised concerns about environmental impact due to high energy consumption. In this work, we introduce BitNet, a scalable and stable 1-bit Transformer architecture designed for large language models. Specifically, we introduce BitLinear as a drop-in replacement of the nn.Linear layer in order to train 1-bit weights from scratch. Experimental results on language modeling show that BitNet achieves competitive performance while substantially reducing memory footprint and energy consumption, compared to state-of-the-art 8-bit quantization methods and FP16 Transformer baselines. Furthermore, BitNet exhibits a scaling law akin to full-precision Transformers, suggesting its potential for effective scaling to even larger language models while maintaining efficiency and performance benefits.

Ningxin Zheng, Huiqiang Jiang, Quanlu Zhang et al. · microsoft-research

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due to significant overheads associated with preprocessing. Efficient execution of dynamic sparse computation often faces the misalignment between the GPU-friendly tile configuration for efficient execution and the sparsity-aware tile shape that minimizes coverage wastes (non-zero values in tensor). In this paper, we propose PIT, a deep-learning compiler for dynamic sparsity. PIT proposes a novel tiling mechanism that leverages Permutation Invariant Transformation (PIT), a mathematically proven property, to transform multiple sparsely located micro-tiles into a GPU-efficient dense tile without changing the computation results, thus achieving both high GPU utilization and low coverage waste. Given a model, PIT first finds feasible PIT rules for all its operators and generates efficient GPU kernels accordingly. At runtime, with the novel SRead and SWrite primitives, PIT rules can be executed extremely fast to support dynamic sparsity in an online manner. Extensive evaluation on diverse models shows that PIT can accelerate dynamic sparsity computation by up to 5.9x (average 2.43x) over state-of-the-art compilers.

Xiaonan Nie, Xupeng Miao, Zilong Wang et al.

With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a huge amount of hardware resources. Recently, sparsely-gated Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. However, such a sparse conditional computation may not be effective as expected in practical systems due to the routing imbalance and fluctuation problems. Generally, MoEs are becoming a new data analytics paradigm in the data life cycle and suffering from unique challenges at scales, complexities, and granularities never before possible. In this paper, we propose a novel DNN training framework, FlexMoE, which systematically and transparently address the inefficiency caused by dynamic dataflow. We first present an empirical analysis on the problems and opportunities of training MoE models, which motivates us to overcome the routing imbalance and fluctuation problems by a dynamic expert management and device placement mechanism. Then we introduce a novel scheduling module over the existing DNN runtime to monitor the data flow, make the scheduling plans, and dynamically adjust the model-to-hardware mapping guided by the real-time data traffic. A simple but efficient heuristic algorithm is exploited to dynamically optimize the device placement during training. We have conducted experiments on both NLP models (e.g., BERT and GPT) and vision models (e.g., Swin). And results show FlexMoE can achieve superior performance compared with existing systems on real-world workloads -- FlexMoE outperforms DeepSpeed by 1.70x on average and up to 2.10x, and outperforms FasterMoE by 1.30x on average and up to 1.45x.

Zhiwen Mo, Lei Wang, Jianyu Wei et al.

Large Language Model (LLM) inference becomes resource-intensive, prompting a shift toward low-bit model weights to reduce the memory footprint and improve efficiency. Such low-bit LLMs necessitate the mixed-precision matrix multiplication (mpGEMM), an important yet underexplored operation involving the multiplication of lower-precision weights with higher-precision activations. Off-the-shelf hardware does not support this operation natively, leading to indirect, thus inefficient, dequantization-based implementations. In this paper, we study the lookup table (LUT)-based approach for mpGEMM and find that a conventional LUT implementation fails to achieve the promised gains. To unlock the full potential of LUT-based mpGEMM, we propose LUT Tensor Core, a software-hardware co-design for low-bit LLM inference. LUT Tensor Core differentiates itself from conventional LUT designs through: 1) software-based optimizations to minimize table precompute overhead and weight reinterpretation to reduce table storage; 2) a LUT-based Tensor Core hardware design with an elongated tiling shape to maximize table reuse and a bit-serial design to support diverse precision combinations in mpGEMM; 3) a new instruction set and compilation optimizations for LUT-based mpGEMM. LUT Tensor Core significantly outperforms existing pure software LUT implementations and achieves a 1.44$\times$ improvement in compute density and energy efficiency compared to previous state-of-the-art LUT-based accelerators.

Yiqi Liu, Yuqi Xue, Yu Cheng et al.

As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on the chip (e.g., Graphcore IPU). It allows each core to directly access the fast scratchpad memory in other cores, which enables new parallel computing paradigms. However, without proper support for the scalable inter-core connections in current DL compilers, it is hard for developers to exploit the benefits of this new architecture. We present T10, the first DL compiler to exploit the inter-core communication bandwidth and distributed on-chip memory on AI chips. To formulate the computation and communication patterns of tensor operators in this new architecture, T10 introduces a distributed tensor abstraction rTensor. T10 maps a DNN model to execution plans with a generalized compute-shift pattern, by partitioning DNN computation into sub-operators and mapping them to cores, so that the cores can exchange data following predictable patterns. T10 makes globally optimized trade-offs between on-chip memory consumption and inter-core communication overhead, selects the best execution plan from a vast optimization space, and alleviates unnecessary inter-core communications. Our evaluation with a real inter-core connected AI chip, the Graphcore IPU, shows up to 3.3$\times$ performance improvement, and scalability support for larger models, compared to state-of-the-art DL compilers and vendor libraries.

Yizhao Gao, Shuming Guo, Shijie Cao et al. · tsinghua

We introduce SeerAttention-R, a sparse attention framework specifically tailored for the long decoding of reasoning models. Extended from SeerAttention, SeerAttention-R retains the design of learning attention sparsity through a self-distilled gating mechanism, while removing query pooling to accommodate auto-regressive decoding. With a lightweight plug-in gating, SeerAttention-R is flexible and can be easily integrated into existing pretrained model without modifying the original parameters. We demonstrate that SeerAttention-R, trained on just 0.4B tokens, maintains near-lossless reasoning accuracy with 4K token budget in AIME benchmark under large sparse attention block sizes (64/128). Using TileLang, we develop a highly optimized sparse decoding kernel that achieves near-theoretical speedups of up to 9x over FlashAttention-3 on H100 GPU at 90% sparsity. Code is available at: https://github.com/microsoft/SeerAttention.

Congjie He, Yeqi Huang, Pei Mu et al. · microsoft-research

Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-chip memory (tens of GB in total) and ultra-high on-chip memory bandwidth (tens of PB/s). However, current LLM inference systems, optimized for shared memory architectures like GPUs, fail to exploit these accelerators fully. We introduce WaferLLM, the first wafer-scale LLM inference system. WaferLLM is guided by a novel PLMR model (pronounced as "Plummer") that captures the unique hardware characteristics of wafer-scale architectures. Leveraging this model, WaferLLM pioneers wafer-scale LLM parallelism, optimizing the utilization of hundreds of thousands of on-chip cores. It also introduces MeshGEMM and MeshGEMV, the first GEMM and GEMV implementations designed to scale effectively on wafer-scale accelerators. Evaluations show that WaferLLM achieves up to 200$\times$ higher accelerator utilization than state-of-the-art methods. Leveraging a wafer-scale accelerator (Cerebras WSE2), WaferLLM delivers GEMV operations 606$\times$ faster and 16$\times$ more energy-efficient than on an NVIDIA A100 GPU. For full LLM inference, WaferLLM achieves 10-20$\times$ speedups over A100 GPU clusters running SGLang and vLLM. These advantages are expected to grow as wafer-scale AI models, software, and hardware continue to mature. WaferLLM is open-sourced at https://github.com/MeshInfra/WaferLLM.

Shuming Ma, Hongyu Wang, Lingxiao Ma et al. · microsoft-research

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.

Zhiwen Mo, Guoyu Li, Hao et al.

Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked accelerators with higher memory bandwidth and capacity. As LLMs scale to hundreds of billions or trillions of parameters, distributed inference across multiple 3D chips becomes essential. With cross-stack co-design increasingly critical, we propose DeepStack, an accurate and efficient performance model and tool to enable early-stage system-hardware co-design space exploration (DSE) for distributed 3D-stacked AI systems. At the hardware level, DeepStack captures fine-grained 3D memory semantics such as transaction-aware bandwidth, bank activation constraints, buffering limitations, and thermal-power modeling. At the system level, DeepStack incorporates comprehensive parallelization strategies and execution scheduling for distributed LLM inference. With novel modeling techniques such as dual-stage network abstraction and tile-level compute-communication overlap, we achieve up to 100,000x faster runtime over state-of-the-art simulators at comparable accuracy, cross-validated against our in-house 3D designs, NS-3 backend (2.12%), and vLLM serving on 8xB200 GPUs (12.18%). With hierarchical design space search, DeepStack enables efficient exploration over 2.5x10^14 design points spanning 3D-stacked DRAM layers, DRAM vertical connectivity, interconnect, compute-memory allocation, and distributed scheduling. Compared with baseline designs, DeepStack achieves up to 9.5x higher throughput through co-optimized parallelism and 3D architecture search. Our DSE further reveals that batch size drives a more fundamental architectural divide than the prefill/decode distinction, and that parallelism strategy and hardware architecture are tightly coupled -- incomplete schedule search leads to permanently suboptimal silicon irrecoverable by software tuning. We intend to open source DeepStack to support future research.

Feiyang Chen, Yu Cheng, Lei Wang et al.

Transformers and large language models (LLMs) have revolutionized machine learning, with attention mechanisms at the core of their success. As the landscape of attention variants expands, so too do the challenges of optimizing their performance, particularly across different hardware platforms. Current optimization strategies are often narrowly focused, requiring extensive manual intervention to accommodate changes in model configurations or hardware environments. In this paper, we introduce AttentionEngine, a comprehensive framework designed to streamline the optimization of attention mechanisms across heterogeneous hardware backends. By decomposing attention computation into modular operations with customizable components, AttentionEngine enables flexible adaptation to diverse algorithmic requirements. The framework further automates kernel optimization through a combination of programmable templates and a robust cross-platform scheduling strategy. Empirical results reveal performance gains of up to 10x on configurations beyond the reach of existing methods. AttentionEngine offers a scalable, efficient foundation for developing and deploying attention mechanisms with minimal manual tuning. Our code has been open-sourced and is available at https://github.com/microsoft/AttentionEngine.

Jianyu Wei, Shijie Cao, Ting Cao et al.

The deployment of Large Language Models (LLMs) on edge devices is increasingly important to enhance on-device intelligence. Weight quantization is crucial for reducing the memory footprint of LLMs on devices. However, low-bit LLMs necessitate mixed precision matrix multiplication (mpGEMM) of low precision weights and high precision activations during inference. Existing systems, lacking native support for mpGEMM, resort to dequantize weights for high precision computation. Such an indirect way can lead to a significant inference overhead. In this paper, we introduce T-MAC, an innovative lookup table(LUT)-based method designed for efficient low-bit LLM (i.e., weight-quantized LLM) inference on CPUs. T-MAC directly supports mpGEMM without dequantization, while simultaneously eliminating multiplications and reducing additions required. Specifically, T-MAC transforms the traditional data-type-centric multiplication to bit-wise table lookup, and enables a unified and scalable mpGEMM solution. Our LUT-based kernels scale linearly to the weight bit-width. Evaluated on low-bit Llama and BitNet models, T-MAC demonstrates up to 4x increase in throughput and 70% reduction in energy consumption compared to llama.cpp. For BitNet-b1.58-3B, T-MAC delivers a token generation throughput of 30 tokens/s with a single core and 71 tokens/s with eight cores on M2-Ultra, and 11 tokens/s on lower-end devices like Raspberry Pi 5, which significantly exceeds the adult average reading speed. T-MAC with LUT-based computing paradigm, paves the way for the practical deployment of low-bit LLMs on resource-constrained edge devices without compromising computational efficiency. The system is open-sourced at https://github.com/microsoft/T-MAC .

Lei Wang, Yu Cheng, Yining Shi et al.

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 on those tiles. However, writing high-performance kernels remains complex despite the clarity of these patterns. Achieving peak performance requires careful, hardware-centric optimizations to fully leverage modern accelerators. While domain-specific compilers attempt to reduce the burden of writing high-performance kernels, they often struggle with usability and expressiveness gaps. In this paper, we present TileLang, a generalized tiled programming model for more efficient AI Kernel programming. TileLang decouples scheduling space (thread binding, layout, tensorize and pipeline) from dataflow, and encapsulated them as a set of customization annotations and primitives. This approach allows users to focus on the kernel's data-flow itself, while leaving most other optimizations to compilers. We conduct comprehensive experiments on commonly-used devices, across numerous experiments, our evaluation shows that TileLang can achieve state-of-the-art performance in key kernels, demonstrating that its unified block-and-thread paradigm and transparent scheduling capabilities deliver both the power and flexibility demanded by modern AI system development.

Hao Mark Chen, Zhiwen Mo, Guanxi Lu et al.

Deploying agentic AI on edge devices is crucial for privacy and responsiveness, but memory constraints typically relegate these systems to smaller Large Language Models (LLMs) with inferior reasoning capabilities. Test-Time Scaling (TTS) can bridge this reasoning gap by dedicating more compute during inference, but existing methods incur prohibitive overhead on edge hardware. To overcome this, we introduce FlashTTS, a serving system that makes TTS practical for memory-constrained LLM reasoning. FlashTTS introduces three synergistic optimizations: (i) Speculative Beam Extension to mitigate system stragglers from irregular reasoning paths; (ii) Asymmetric Multi-Model Memory Allocation to dynamically balance memory between generation and verification; and (iii) Dynamic Prefix-Aware Scheduling to maximize KV-cache reuse. Built as a plug-and-play library for vLLM, FlashTTS enables edge LLMs on a single consumer GPU (24 GB) to match the accuracy and latency of large cloud models. Our evaluation demonstrates that FlashTTS achieves an average 2.2x higher goodput and reduces latency by 38%-68% compared to a vLLM baseline, paving the way for democratized, high-performance agentic AI on edge devices.

Xiaonan Nie, Xupeng Miao, Shijie Cao et al.

Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i.e., a small pieces of the full model), MoE can easily increase the model parameters to a very large scale while keeping the computation cost in a constant level. Most existing works just initialize some random experts, set a fixed gating strategy (e.g., Top-k), and train the model from scratch in an ad-hoc way. We identify that these MoE models are suffering from the immature experts and unstable sparse gate, which are harmful to the convergence performance. In this paper, we propose an efficient end-to-end MoE training framework called EvoMoE. EvoMoE starts from training one single expert and gradually evolves into a large and sparse MoE structure. EvoMoE mainly contains two phases: the expert-diversify phase to train the base expert for a while and spawn multiple diverse experts from it, and the gate-sparsify phase to learn an adaptive sparse gate and activate a dynamic number of experts. EvoMoE naturally decouples the joint learning of both the experts and the sparse gate and focuses on learning the basic knowledge with a single expert at the early training stage. Then it diversifies the experts and continues to train the MoE with a novel Dense-to-Sparse gate (DTS-Gate). Specifically, instead of using a permanent sparse gate, DTS-Gate begins as a dense gate that routes tokens to all experts, then gradually and adaptively becomes sparser while routes to fewer experts. Evaluations are conducted on three popular models and tasks, including RoBERTa for masked language modeling task, GPT for language modeling task and Transformer for machine translation task. The results show that EvoMoE outperforms existing baselines, including Switch, BASE Layer, Hash Layer and StableMoE.

Zhihui Zhang, Jingwen Leng, Lingxiao Ma et al.

Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures. It is becoming more and more popular due to its high accuracy achieved in many graph-related tasks. However, GNN is not as well understood in the system and architecture community as its counterparts such as multi-layer perceptrons and convolutional neural networks. This work tries to introduce the GNN to our community. In contrast to prior work that only presents characterizations of GCNs, our work covers a large portion of the varieties for GNN workloads based on a general GNN description framework. By constructing the models on top of two widely-used libraries, we characterize the GNN computation at inference stage concerning general-purpose and application-specific architectures and hope our work can foster more system and architecture research for GNNs.

Lingxiao Ma, Zhi Yang, Youshan Miao et al.

Recent deep learning models have moved beyond low-dimensional regular grids such as image, video, and speech, to high-dimensional graph-structured data, such as social networks, brain connections, and knowledge graphs. This evolution has led to large graph-based irregular and sparse models that go beyond what existing deep learning frameworks are designed for. Further, these models are not easily amenable to efficient, at scale, acceleration on parallel hardwares (e.g. GPUs). We introduce NGra, the first parallel processing framework for graph-based deep neural networks (GNNs). NGra presents a new SAGA-NN model for expressing deep neural networks as vertex programs with each layer in well-defined (Scatter, ApplyEdge, Gather, ApplyVertex) graph operation stages. This model not only allows GNNs to be expressed intuitively, but also facilitates the mapping to an efficient dataflow representation. NGra addresses the scalability challenge transparently through automatic graph partitioning and chunk-based stream processing out of GPU core or over multiple GPUs, which carefully considers data locality, data movement, and overlapping of parallel processing and data movement. NGra further achieves efficiency through highly optimized Scatter/Gather operators on GPUs despite its sparsity. Our evaluation shows that NGra scales to large real graphs that none of the existing frameworks can handle directly, while achieving up to about 4 times speedup even at small scales over the multiple-baseline design on TensorFlow.