MoE-CAP: Cost-Accuracy-Performance Benchmarking for Mixture-of-Experts Systems

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently; however, MoE systems rely on heterogeneous compute and memory resources. These factors collectively influence the system's Cost, Accuracy, and Performance (CAP), creating a challenging trade-off. Current benchmarks often fail to provide precise estimates of these effects, complicating practical considerations for deploying MoE systems. To bridge this gap, we introduce MoE-CAP, a benchmark specifically designed to evaluate MoE systems. Our findings highlight the difficulty of achieving an optimal balance of cost, accuracy, and performance with existing hardware capabilities. MoE systems often necessitate compromises on one factor to optimize the other two, a dynamic we term the MoE-CAP trade-off. To identify the best trade-off, we propose novel performance evaluation metrics - Sparse Memory Bandwidth Utilization (S-MBU) and Sparse Model FLOPS Utilization (S-MFU) - and develop cost models that account for the heterogeneous compute and memory hardware integral to MoE systems. This benchmark is publicly available on HuggingFace: https://huggingface.co/spaces/sparse-generative-ai/open-moe-llm-leaderboard.

PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis

View synthesis using Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) has demonstrated impressive fidelity in rendering real-world scenarios. However, practical methods for accurate and efficient epistemic Uncertainty Quantification (UQ) in view synthesis are lacking. Existing approaches for NeRF either introduce significant computational overhead (e.g., ``10x increase in training time" or ``10x repeated training") or are limited to specific uncertainty conditions or models. Notably, GS models lack any systematic approach for comprehensive epistemic UQ. This capability is crucial for improving the robustness and scalability of neural view synthesis, enabling active model updates, error estimation, and scalable ensemble modeling based on uncertainty. In this paper, we revisit NeRF and GS-based methods from a function approximation perspective, identifying key differences and connections in 3D representation learning. Building on these insights, we introduce PH-Dropout (Post hoc Dropout), the first real-time and accurate method for epistemic uncertainty estimation that operates directly on pre-trained NeRF and GS models. Extensive evaluations validate our theoretical findings and demonstrate the effectiveness of PH-Dropout.

PH-Dropout: Prctical Epistemic Uncertainty Quantification for View Synthesis

View synthesis using Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) has demonstrated impressive fidelity in rendering real-world scenarios. However, practical methods for accurate and efficient epistemic Uncertainty Quantification (UQ) in view synthesis are lacking. Existing approaches for NeRF either introduce significant computational overhead (e.g., ``10x increase in training time" or ``10x repeated training") or are limited to specific uncertainty conditions or models. Notably, GS models lack any systematic approach for comprehensive epistemic UQ. This capability is crucial for improving the robustness and scalability of neural view synthesis, enabling active model updates, error estimation, and scalable ensemble modeling based on uncertainty. In this paper, we revisit NeRF and GS-based methods from a function approximation perspective, identifying key differences and connections in 3D representation learning. Building on these insights, we introduce PH-Dropout (Post hoc Dropout), the first real-time and accurate method for epistemic uncertainty estimation that operates directly on pre-trained NeRF and GS models. Extensive evaluations validate our theoretical findings and demonstrate the effectiveness of PH-Dropout.

Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding

Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent kernels. Despite their effectiveness, existing PEs require manual, empirical adjustment of crucial hyperparameters, specifically the Fourier features, tailored to each unique task. Further, PEs face challenges in efficiently learning high-frequency functions, particularly in tasks with limited data. In this paper, we introduce sinusoidal PE (SPE), designed to efficiently learn adaptive frequency features closely aligned with the true underlying function. Our experiments demonstrate that SPE, without hyperparameter tuning, consistently achieves enhanced fidelity and faster training across various tasks, including 3D view synthesis, Text-to-Speech generation, and 1D regression. SPE is implemented as a direct replacement for existing PEs. Its plug-and-play nature lets numerous tasks easily adopt and benefit from SPE.

MoE-Infinity: Activation-Aware Expert Offloading for Efficient MoE Serving

This paper presents MoE-Infinity, a cost-efficient mixture-of-expert (MoE) serving system that realizes activation-aware expert offloading. MoE-Infinity features sequence-level expert activation tracing, a new approach adept at identifying sparse activations and capturing the temporal locality of MoE inference. By analyzing these traces, MoE-Infinity performs novel activation-aware expert prefetching and caching, substantially reducing the latency overheads usually associated with offloading experts for improved cost performance. Extensive experiments in a cluster show that MoE-Infinity outperforms numerous existing systems and approaches, reducing latency by 4 - 20X and decreasing deployment costs by over 8X for various MoEs. MoE-Infinity's source code is publicly available at https://github.com/TorchMoE/MoE-Infinity

ServerlessLLM: Locality-Enhanced Serverless Inference for Large Language Models

This paper presents ServerlessLLM, a locality-enhanced serverless inference system for Large Language Models (LLMs). ServerlessLLM exploits the substantial capacity and bandwidth of storage and memory devices available on GPU servers, thereby reducing costly remote checkpoint downloads and achieving efficient checkpoint loading. ServerlessLLM achieves this through three main contributions: (i) fast LLM checkpoint loading via a novel loading-optimized checkpoint format design, coupled with an efficient multi-tier checkpoint loading system; (ii) locality-driven LLM inference with live migration, which allows ServerlessLLM to effectively achieve locality-driven server allocation while preserving the low latency of ongoing LLM inference; and (iii) locality-aware server allocation, enabling ServerlessLLM to evaluate the status of each server in a cluster and effectively schedule model startup time to capitalize on local checkpoint placement. Our comprehensive experiments, which include microbenchmarks and real-world traces, show that ServerlessLLM surpasses state-of-the-art systems by 10 - 200X in latency performance when running various LLM inference workloads.

TENPLEX: Changing Resources of Deep Learning Jobs using Parallelizable Tensor Collections

Deep learning (DL) jobs use multi-dimensional parallelism, i.e they combine data, model, and pipeline parallelism, to use large GPU clusters efficiently. This couples jobs tightly to a set of GPU devices, but jobs may experience changes to the device allocation: (i) resource elasticity during training adds or removes devices; (ii) hardware maintenance may require redeployment on different devices; and (iii) device failures force jobs to run with fewer devices. Current DL frameworks lack support for these scenarios, as they cannot change the multi-dimensional parallelism of an already-running job in an efficient and model-independent way. We describe Tenplex, a state management library for DL frameworks that enables jobs to change the GPU allocation and job parallelism at runtime. Tenplex achieves this by externalizing the DL job state during training as a parallelizable tensor collection (PTC). When the GPU allocation for the DL job changes, Tenplex uses the PTC to transform the DL job state: for the dataset state, Tenplex repartitions it under data parallelism and exposes it to workers through a virtual file system; for the model state, Tenplex obtains it as partitioned checkpoints and transforms them to reflect the new parallelization configuration. For efficiency, these PTC transformations are executed in parallel with a minimum amount of data movement between devices and workers. Our experiments show that Tenplex enables DL jobs to support dynamic parallelization with low overhead.

GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb face considerable bottlenecks in memory, computation, and communication. GEAR, however, optimizes memory efficiency by enabling the memory resources on GPU servers (including host memory and device memory) to manage trajectory data. Furthermore, it facilitates decentralized GPU devices to expedite various trajectory selection strategies, circumventing computational bottlenecks. GEAR is equipped with GPU kernels capable of collecting trajectories using zero-copy access to host memory, along with remote-directed-memory access over InfiniBand, improving communication efficiency. Cluster experiments have shown that GEAR can achieve performance levels up to 6x greater than Reverb when training state-of-the-art large RL models. GEAR is open-sourced at https://github.com/bigrl-team/gear.

Large Sequence Models for Sequential Decision-Making: A Survey

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally designed for prediction problems, it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems, which are typically beset by long-standing issues involving sample efficiency, credit assignment, and partial observability. In recent years, sequence models, especially the Transformer, have attracted increasing interest in the RL communities, spawning numerous approaches with notable effectiveness and generalizability. This survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with sequence models such as the Transformer, by discussing the connection between sequential decision-making and sequence modeling, and categorizing them based on the way they utilize the Transformer. Moreover, this paper puts forth various potential avenues for future research intending to improve the effectiveness of large sequence models for sequential decision-making, encompassing theoretical foundations, network architectures, algorithms, and efficient training systems. As this article has been accepted by the Frontiers of Computer Science, here is an early version, and the most up-to-date version can be found at https://journal.hep.com.cn/fcs/EN/10.1007/s11704-023-2689-5

Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness

Systems for serving inference requests on graph neural networks (GNN) must combine low latency with high throughout, but they face irregular computation due to skew in the number of sampled graph nodes and aggregated GNN features. This makes it challenging to exploit GPUs effectively: using GPUs to sample only a few graph nodes yields lower performance than CPU-based sampling; and aggregating many features exhibits high data movement costs between GPUs and CPUs. Therefore, current GNN serving systems use CPUs for graph sampling and feature aggregation, limiting throughput. We describe Quiver, a distributed GPU-based GNN serving system with low-latency and high-throughput. Quiver's key idea is to exploit workload metrics for predicting the irregular computation of GNN requests, and governing the use of GPUs for graph sampling and feature aggregation: (1) for graph sampling, Quiver calculates the probabilistic sampled graph size, a metric that predicts the degree of parallelism in graph sampling. Quiver uses this metric to assign sampling tasks to GPUs only when the performance gains surpass CPU-based sampling; and (2) for feature aggregation, Quiver relies on the feature access probability to decide which features to partition and replicate across a distributed GPU NUMA topology. We show that Quiver achieves up to 35 times lower latency with an 8 times higher throughput compared to state-of-the-art GNN approaches (DGL and PyG).