arXiv subjects

Yanqi Zhou

Publications and source records attributed to Yanqi Zhou.

At least 19 recordsLinked to original sources

arXiv2025

Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony

Mixture-of-Experts (MoE) architectures offer the promise of larger model capacity without the prohibitive costs of fully dense designs. However, in real-world inference serving, load skew across experts often leads to suboptimal device utilization and excessive synchronization overheads. This paper introduces Asynchronous Expert Parallelism (AEP), a new paradigm that decouples layer execution from barrier-style synchronization. By dynamically queuing tokens at each layer (referred to as $\mu$-queuing) and adaptively re-batching them on demand, GPUs avoid waiting for straggling experts and instead continuously process whichever layer is ready. This asynchronous approach mitigates two major inefficiencies in traditional expert-parallel systems: (1) idle GPU time while waiting for the hottest expert, and (2) small-batch executions on colder experts that waste memory bandwidth. We implement these ideas in a serving system called AMoE, which disaggregates attention from expert layers and uses a defragging scheduler to reduce batch fragmentation. Evaluations on prototype MoE models show that AMoE improves throughput by up to 2.7x compared to state-of-the-art baselines, incurring a manageable latency penalty and providing a cost-effective operating point. Furthermore, experiments demonstrate nearly linear scalability to multi-node settings, whereas the baseline system shows no throughput increase even when the number of GPUs is doubled.

cs.DC↗

arXiv2025

IC-Cache: Efficient Large Language Model Serving via In-context Caching

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs have semantically similar counterparts, suggesting the potential for knowledge transfer among requests. However, naively caching and reusing past responses leads to a big quality drop. In this paper, we introduce IC-Cache, a caching system that enables live LLM capability augmentation to improve serving efficiency: by leveraging historical request-response pairs from larger models as in-context examples, IC-Cache empowers small LLMs to imitate and even exceed the compositional abilities (e.g., reasoning) of their larger counterparts, enabling selective offloading of requests to reduce cost and latency. Achieving this live augmentation at scale introduces intricate trade-offs between response quality, latency, and system throughput. For a new request, IC-Cache efficiently selects similar, high-utility examples to prepend them to the new request's input. At scale, it adaptively routes requests across LLMs of varying capabilities, accounting for response quality and serving loads. IC-Cache employs a cost-aware cache replay mechanism that refines example quality offline to maximize online cache utility and efficiency. Evaluations on millions of realistic requests demonstrate that IC-Cache improves LLM serving throughput by 1.4-5.9x and reduces latency by 28-71% without hurting response quality.

cs.LG↗

arXiv2024

Scalable Multi-Domain Adaptation of Language Models using Modular Experts

Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods often struggle to balance domain-specific performance, retention of general knowledge, and efficiency for training and inference. To address these challenges, we propose Modular Domain Experts (MoDE). MoDE is a mixture-of-experts architecture that augments a general PLMs with modular, domain-specialized experts. These experts are trained independently and composed together via a lightweight training process. In contrast to standard low-rank adaptation methods, each MoDE expert consists of several transformer layers which scale better with more training examples and larger parameter counts. Our evaluation demonstrates that MoDE achieves comparable target performances to full parameter fine-tuning while achieving 1.65% better retention performance. Moreover, MoDE's architecture enables flexible sharding configurations and improves training speeds by up to 38% over state-of-the-art distributed training configurations.

cs.CL↗

arXiv2024

SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention

Multi-head-self-attention (MHSA) mechanisms achieve state-of-the-art (SOTA) performance across natural language processing and vision tasks. However, their quadratic dependence on sequence lengths has bottlenecked inference speeds. To circumvent this bottleneck, researchers have proposed various sparse-MHSA models, where a subset of full attention is computed. Despite their promise, current sparse libraries and compilers do not support high-performance implementations for diverse sparse-MHSA patterns due to the underlying sparse formats they operate on. These formats, which are typically designed for high-performance & scientific computing applications, are either curated for extreme amounts of random sparsity (<1% non-zero values), or specific sparsity patterns. However, the sparsity patterns in sparse-MHSA are moderately sparse (10-50% non-zero values) and varied, resulting in existing sparse-formats trading off generality for performance. We bridge this gap, achieving both generality and performance, by proposing a novel sparse format: affine-compressed-sparse-row (ACSR) and supporting code-generation scheme, SPLAT, that generates high-performance implementations for diverse sparse-MHSA patterns on GPUs. Core to our proposed format and code generation algorithm is the observation that common sparse-MHSA patterns have uniquely regular geometric properties. These properties, which can be analyzed just-in-time, expose novel optimizations and tiling strategies that SPLAT exploits to generate high-performance implementations for diverse patterns. To demonstrate SPLAT's efficacy, we use it to generate code for various sparse-MHSA models, achieving geomean speedups of 2.05x and 4.05x over hand-written kernels written in triton and TVM respectively on A100 GPUs. Moreover, its interfaces are intuitive and easy to use with existing implementations of MHSA in JAX.

cs.PL↗

arXiv2023

FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention

Many efficient $\textit{approximate}$ self-attention techniques have become prevalent since the inception of the transformer architecture. Two popular classes of these techniques are low-rank and kernel methods. Each of these methods has its strengths. We observe these strengths synergistically complement each other and exploit them to fuse low-rank and kernel methods, producing a new class of transformers: FLuRKA ($\textbf{F}$ast $\textbf{L}$ow-$\textbf{R}$ank & $\textbf{K}$ernel$ \textbf{A}$ttention). FLuRKA are highly $\textit{training-efficient}$ with faster model speeds $\textit{and}$ similar model qualities compared to constituent low-rank and kernel methods. We theoretically and empirically evaluate the speed and quality of FLuRKA. Our model speed analysis posits a variety of parameter configurations where FLuRKA exhibit speedups over low-rank and kernel approximations and our model quality analysis bounds the error of FLuRKA with respect to full-attention. Empirically, we instantiate three FLuRKA variants which experience speedups of up to 3.3x and 1.7x over low-rank and kernel methods respectively. This translates to speedups of up to 20x over models with flash-attention. Across a diverse set of tasks spanning language modeling, language understanding, long sequence modeling, machine translation, and image classification, FLuRKA achieve comparable accuracy with underlying low-rank and kernel approximations, occasionally surpassing both.

cs.LG↗

arXiv2023

Brainformers: Trading Simplicity for Efficiency

Transformers are central to recent successes in natural language processing and computer vision. Transformers have a mostly uniform backbone where layers alternate between feed-forward and self-attention in order to build a deep network. Here we investigate this design choice and find that more complex blocks that have different permutations of layer primitives can be more efficient. Using this insight, we develop a complex block, named Brainformer, that consists of a diverse sets of layers such as sparsely gated feed-forward layers, dense feed-forward layers, attention layers, and various forms of layer normalization and activation functions. Brainformer consistently outperforms the state-of-the-art dense and sparse Transformers, in terms of both quality and efficiency. A Brainformer model with 8 billion activated parameters per token demonstrates 2x faster training convergence and 5x faster step time compared to its GLaM counterpart. In downstream task evaluation, Brainformer also demonstrates a 3% higher SuperGLUE score with fine-tuning compared to GLaM with a similar number of activated parameters. Finally, Brainformer largely outperforms a Primer dense model derived with NAS with similar computation per token on fewshot evaluations.

cs.LG↗

arXiv2023

Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models

Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches, as we find that MoE models benefit more from instruction tuning than dense models. In particular, we conduct empirical studies across three experimental setups: (i) Direct finetuning on individual downstream tasks devoid of instruction tuning; (ii) Instructiontuning followed by in-context few-shot or zero-shot generalization on downstream tasks; and (iii) Instruction tuning supplemented by further finetuning on individual downstream tasks. In the first scenario, MoE models overall underperform dense models of identical computational capacity. This narrative, however, dramatically changes with the introduction of instruction tuning (second and third scenario), used independently or in conjunction with task-specific finetuning. Our most powerful model, FLAN-MOE-32B, surpasses the performance of FLAN-PALM-62B on four benchmark tasks, while using only a third of the FLOPs. The advancements embodied byFLAN-MOE inspire a reevaluation of the design principles of large-scale, high-performance language models in the framework of task-agnostic learning.

cs.CL↗

arXiv2023

GiPH: Generalizable Placement Learning for Adaptive Heterogeneous Computing

Careful placement of a computational application within a target device cluster is critical for achieving low application completion time. The problem is challenging due to its NP-hardness and combinatorial nature. In recent years, learning-based approaches have been proposed to learn a placement policy that can be applied to unseen applications, motivated by the problem of placing a neural network across cloud servers. These approaches, however, generally assume the device cluster is fixed, which is not the case in mobile or edge computing settings, where heterogeneous devices move in and out of range for a particular application. We propose a new learning approach called GiPH, which learns policies that generalize to dynamic device clusters via 1) a novel graph representation gpNet that efficiently encodes the information needed for choosing a good placement, and 2) a scalable graph neural network (GNN) that learns a summary of the gpNet information. GiPH turns the placement problem into that of finding a sequence of placement improvements, learning a policy for selecting this sequence that scales to problems of arbitrary size. We evaluate GiPH with a wide range of task graphs and device clusters and show that our learned policy rapidly find good placements for new problem instances. GiPH finds placements with up to 30.5% lower completion times, searching up to 3X faster than other search-based placement policies.

cs.LG↗

arXiv2023

Learning Large Graph Property Prediction via Graph Segment Training

Learning to predict properties of large graphs is challenging because each prediction requires the knowledge of an entire graph, while the amount of memory available during training is bounded. Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint. GST first divides a large graph into segments and then backpropagates through only a few segments sampled per training iteration. We refine the GST paradigm by introducing a historical embedding table to efficiently obtain embeddings for segments not sampled for backpropagation. To mitigate the staleness of historical embeddings, we design two novel techniques. First, we finetune the prediction head to fix the input distribution shift. Second, we introduce Stale Embedding Dropout to drop some stale embeddings during training to reduce bias. We evaluate our complete method GST-EFD (with all the techniques together) on two large graph property prediction benchmarks: MalNet and TpuGraphs. Our experiments show that GST-EFD is both memory-efficient and fast, while offering a slight boost on test accuracy over a typical full graph training regime.

cs.LG↗

arXiv2023

Lifelong Language Pretraining with Distribution-Specialized Experts

Pretraining on a large-scale corpus has become a standard method to build general language models (LMs). Adapting a model to new data distributions targeting different downstream tasks poses significant challenges. Naive fine-tuning may incur catastrophic forgetting when the over-parameterized LMs overfit the new data but fail to preserve the pretrained features. Lifelong learning (LLL) aims to enable information systems to learn from a continuous data stream across time. However, most prior work modifies the training recipe assuming a static fixed network architecture. We find that additional model capacity and proper regularization are key elements to achieving strong LLL performance. Thus, we propose Lifelong-MoE, an extensible MoE (Mixture-of-Experts) architecture that dynamically adds model capacity via adding experts with regularized pretraining. Our results show that by only introducing a limited number of extra experts while keeping the computation cost constant, our model can steadily adapt to data distribution shifts while preserving the previous knowledge. Compared to existing lifelong learning approaches, Lifelong-MoE achieves better few-shot performance on 19 downstream NLP tasks.

cs.CL↗

arXiv2023

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches to enable a new way of balancing speed and accuracy using conditional computation. Starting with an existing dense pretrained model, CoDA adds sparse activation together with a small number of new parameters and a light-weight training phase. Our experiments demonstrate that the CoDA approach provides an unexpectedly efficient way to transfer knowledge. Across a variety of language, vision, and speech tasks, CoDA achieves a 2x to 8x inference speed-up compared to the state-of-the-art Adapter approaches with moderate to no accuracy loss and the same parameter efficiency.

cs.CL↗

arXiv2022

Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search

In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture Search (NAS) can work in synergy to greatly benefit on-device Dense Predictions (DP). Empirical results reveal that the joint learning of the two paradigms is surprisingly effective at improving DP accuracy, achieving superior performance over both the transfer learning of single-task NAS and prior state-of-the-art approaches in MTL, all with just 1/10th of the computation. To the best of our knowledge, our framework, named EDNAS, is the first to successfully leverage the synergistic relationship of NAS and MTL for DP. Our second key insight is that the standard depth training for multi-task DP can cause significant instability and noise to MTL evaluation. Instead, we propose JAReD, an improved, easy-to-adopt Joint Absolute-Relative Depth loss, that reduces up to 88% of the undesired noise while simultaneously boosting accuracy. We conduct extensive evaluations on standard datasets, benchmark against strong baselines and state-of-the-art approaches, as well as provide an analysis of the discovered optimal architectures.

cs.CV↗

arXiv2022

Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs

On-device ML accelerators are becoming a standard in modern mobile system-on-chips (SoC). Neural architecture search (NAS) comes to the rescue for efficiently utilizing the high compute throughput offered by these accelerators. However, existing NAS frameworks have several practical limitations in scaling to multiple tasks and different target platforms. In this work, we provide a two-pronged approach to this challenge: (i) a NAS-enabling infrastructure that decouples model cost evaluation, search space design, and the NAS algorithm to rapidly target various on-device ML tasks, and (ii) search spaces crafted from group convolution based inverted bottleneck (IBN) variants that provide flexible quality/performance trade-offs on ML accelerators, complementing the existing full and depthwise convolution based IBNs. Using this approach we target a state-of-the-art mobile platform, Google Tensor SoC, and demonstrate neural architectures that improve the quality-performance pareto frontier for various computer vision (classification, detection, segmentation) as well as natural language processing tasks.

cs.DC↗

arXiv2022

Mixture-of-Experts with Expert Choice Routing

Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing strategy (e.g. one resulting in load imbalance) can cause certain experts to be under-trained, leading to an expert being under or over-specialized. Prior work allocates a fixed number of experts to each token using a top-k function regardless of the relative importance of different tokens. To address this, we propose a heterogeneous mixture-of-experts employing an expert choice method. Instead of letting tokens select the top-k experts, we have experts selecting the top-k tokens. As a result, each token can be routed to a variable number of experts and each expert can have a fixed bucket size. We systematically study pre-training speedups using the same computational resources of the Switch Transformer top-1 and GShard top-2 gating of prior work and find that our method improves training convergence time by more than 2x. For the same computational cost, our method demonstrates higher performance in fine-tuning 11 selected tasks in the GLUE and SuperGLUE benchmarks. For a smaller activation cost, our method outperforms the T5 dense model in 7 out of the 11 tasks.

cs.LG↗

arXiv2022

LaMDA: Language Models for Dialog Applications

We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog data and web text. While model scaling alone can improve quality, it shows less improvements on safety and factual grounding. We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding. The first challenge, safety, involves ensuring that the model's responses are consistent with a set of human values, such as preventing harmful suggestions and unfair bias. We quantify safety using a metric based on an illustrative set of human values, and we find that filtering candidate responses using a LaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promising approach to improving model safety. The second challenge, factual grounding, involves enabling the model to consult external knowledge sources, such as an information retrieval system, a language translator, and a calculator. We quantify factuality using a groundedness metric, and we find that our approach enables the model to generate responses grounded in known sources, rather than responses that merely sound plausible. Finally, we explore the use of LaMDA in the domains of education and content recommendations, and analyze their helpfulness and role consistency.

cs.CL↗

arXiv2021

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However, training these large dense models requires significant amounts of computing resources. In this paper, we propose and develop a family of language models named GLaM (Generalist Language Model), which uses a sparsely activated mixture-of-experts architecture to scale the model capacity while also incurring substantially less training cost compared to dense variants. The largest GLaM has 1.2 trillion parameters, which is approximately 7x larger than GPT-3. It consumes only 1/3 of the energy used to train GPT-3 and requires half of the computation flops for inference, while still achieving better overall zero-shot and one-shot performance across 29 NLP tasks.

cs.CL↗

arXiv2021

A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules

Multi-Chip-Modules (MCMs) reduce the design and fabrication cost of machine learning (ML) accelerators while delivering performance and energy efficiency on par with a monolithic large chip. However, ML compilers targeting MCMs need to solve complex optimization problems optimally and efficiently to achieve this high performance. One such problem is the multi-chip partitioning problem where compilers determine the optimal partitioning and placement of operations in tensor computation graphs on chiplets in MCMs. Partitioning ML graphs for MCMs is particularly hard as the search space grows exponentially with the number of chiplets available and the number of nodes in the neural network. Furthermore, the constraints imposed by the underlying hardware produce a search space where valid solutions are extremely sparse. In this paper, we present a strategy using a deep reinforcement learning (RL) framework to emit a possibly invalid candidate partition that is then corrected by a constraint solver. Using the constraint solver ensures that RL encounters valid solutions in the sparse space frequently enough to converge with fewer samples as compared to non-learned strategies. The architectural choices we make for the policy network allow us to generalize across different ML graphs. Our evaluation of a production-scale model, BERT, on real hardware reveals that the partitioning generated using RL policy achieves 6.11% and 5.85% higher throughput than random search and simulated annealing. In addition, fine-tuning the pre-trained RL policy reduces the search time from 3 hours to only 9 minutes, while achieving the same throughput as training RL policy from scratch.

cs.LG↗

arXiv2021

Do Transformer Modifications Transfer Across Implementations and Applications?

The research community has proposed copious modifications to the Transformer architecture since it was introduced over three years ago, relatively few of which have seen widespread adoption. In this paper, we comprehensively evaluate many of these modifications in a shared experimental setting that covers most of the common uses of the Transformer in natural language processing. Surprisingly, we find that most modifications do not meaningfully improve performance. Furthermore, most of the Transformer variants we found beneficial were either developed in the same codebase that we used or are relatively minor changes. We conjecture that performance improvements may strongly depend on implementation details and correspondingly make some recommendations for improving the generality of experimental results.

cs.LG↗