BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Danyang Zhuo

Danyang Zhuo contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Distributed, Parallel, and Cluster ComputingArtificial IntelligenceMachine LearningDatabasesOperating SystemsProgramming LanguagesInformation RetrievalNetworking and Internet ArchitecturePerformanceSoftware Engineering

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

Curator: Efficient Vector Search with Low-Selectivity Filters

Embedding-based dense retrieval has become the cornerstone of many critical applications, where approximate nearest neighbor search (ANNS) queries are often combined with filters on labels such as dates and price ranges. Graph-based indexes achieve state-of-the-art performance on unfiltered ANNS but encounter connectivity breakdown on low-selectivity filtered queries, where qualifying vectors become sparse and the graph structure among them fragments. Recent research proposes specialized graph indexes that address this issue by expanding graph degree, which incurs prohibitively high construction costs. Given these inherent limitations of graph-based methods, we argue for a dual-index architecture and present Curator, a partition-based index that complements existing graph-based approaches for low-selectivity filtered ANNS. Curator builds specialized indexes for different labels within a shared clustering tree, where each index adapts to the distribution of its qualifying vectors to ensure efficient search while sharing structure to minimize memory overhead. The system also supports incremental updates and handles arbitrary complex predicates beyond single-label filters by efficiently constructing temporary indexes on the fly. Our evaluation demonstrates that integrating Curator with state-of-the-art graph indexes reduces low-selectivity query latency by up to 20.9x compared to pre-filtering fallback, while increasing construction time and memory footprint by only 5.5% and 4.3%, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast

SVD-based Low-rank compression reduces transformer parameters and nominal FLOPs, but these savings often translate poorly into real LLM serving speedups. We show that this gap is largely a runtime problem: factorized checkpoints fragment execution paths, and the resulting overhead differs substantially between prefill and autoregressive decode. We present FlashSVD v1.5, a unified inference runtime for serving SVD-compressed transformers. FlashSVD v1.5 maps diverse public SVD compression families to a common factorized representation and combines phase-specific kernels with dense-KV decode, packed MLP execution, and per-layer CUDA-graph replay to reorganize the low-rank serving path into a thin runtime. Across representative decoder-serving settings, FlashSVD v1.5 achieves up to 2.55x decode and 2.39x end-to-end speedup, and it attains 1.48x average decode and 1.44x average end-to-end speedup across multiple popular SVD compression families. These results suggest that practical low-rank acceleration requires runtime co-design, not compression algorithms alone. Our code is available at: https://github.com/Zishan-Shao/FlashSVD.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support

Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static errors are costly in both latency and token consumption. Post-hoc repair delays error detection until generation completes and commonly regenerates large regions of previously valid code. Constrained semantic decoding checks after each token, incurring per-token overhead while limiting repair to the current token even when the root cause lies earlier. We present Hydra, a system for efficient recovery from static errors during code generation. Hydra allows checking to proceed asynchronously with generation, avoiding checker overhead when the generated code is semantically correct. In addition, it provides checkpoint-and-rollback support for targeted repair, avoiding regeneration and rechecking of valid prefixes. We retrofit the Clang C/C++ compiler to support Hydra with modest modifications. Paired with a token-efficient repair strategy, Hydra reduces latency by up to 71% and token consumption by up to 70% relative to post-hoc repair on C/C++ code generation tasks that encounter static errors.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs

Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs, consumer GPUs serve single-user, rapidly changing workloads, and each model's working set often nearly fills the GPU memory. As a result, existing sharing mechanisms (e.g., NVIDIA Unified Virtual Memory) perform poorly due to memory thrashing and excessive use of CPU pinned memory when multiple applications are active. We design and implement Nixie, a system that enables efficient and transparent temporal multiplexing on consumer GPUs without requiring any application or driver changes. Nixie is a system service that coordinates GPU memory allocation and kernel launch behavior to efficiently utilize the CPU-GPU bi-directional bandwidth and CPU pinned memory. A lightweight scheduler in Nixie further improves responsiveness by automatically prioritizing latency-sensitive interactive jobs using MLFQ-inspired techniques. Our evaluations show that Nixie improves latency of real interactive code-completion tasks by up to $3.8\times$ and saves up to 66.8% CPU pinned memory usage given the same latency requirement.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Parallel Prefix Verification for Speculative Generation

We introduce PARSE (PArallel pRefix Speculative Engine), a speculative generation framework that accelerates large language model (LLM) inference by parallelizing prefix verification on a semantic level. Existing speculative decoding methods are fundamentally limited by token-level equivalence: the target model must verify each token, leading to short acceptance lengths and modest speedups. Moving to semantic or segment-level verification can substantially increase acceptance granularity, but prior approaches rely on sequential verification, introducing significant overhead and limiting practical gains. PARSE introduces parallel prefix verification, enabling semantic-level verification without sequential checks. Given a full draft from a draft model, the target model evaluates correctness across multiple prefixes in a single forward pass using a custom attention mask, directly identifying the maximal valid prefix. This eliminates sequential segment verification, and makes verification compute-efficient. PARSE is orthogonal to token-level speculative decoding and can be composed with it for additional gains. Across models and benchmarks, PARSE delivers $1.25\times$ to $4.3\times$ throughput gain over the target model, and $1.6\times$ to $4.5\times$ when composed with EAGLE-3, all with negligible accuracy degradation. This demonstrates parallel prefix verification as an effective, general approach to accelerating LLM inference.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning

Alpa automates model-parallel training of large deep learning (DL) models by generating execution plans that unify data, operator, and pipeline parallelism. Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations. They do not suffice to scale out complex DL models on distributed compute devices. Alpa distributes the training of large DL models by viewing parallelisms as two hierarchical levels: inter-operator and intra-operator parallelisms. Based on it, Alpa constructs a new hierarchical space for massive model-parallel execution plans. Alpa designs a number of compilation passes to automatically derive efficient parallel execution plans at each parallelism level. Alpa implements an efficient runtime to orchestrate the two-level parallel execution on distributed compute devices. Our evaluation shows Alpa generates parallelization plans that match or outperform hand-tuned model-parallel training systems even on models they are designed for. Unlike specialized systems, Alpa also generalizes to models with heterogeneous architectures and models without manually-designed plans. Alpa's source code is publicly available at https://github.com/alpa-projects/alpa

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dissecting Service Mesh Overheads

Service meshes play a central role in the modern application ecosystem by providing an easy and flexible way to connect different services that form a distributed application. However, because of the way they interpose on application traffic, they can substantially increase application latency and resource consumption. We develop a decompositional approach and a tool, called MeshInsight, to systematically characterize the overhead of service meshes and to help developers quantify overhead in deployment scenarios of interest. Using MeshInsight, we confirm that service meshes can have high overhead -- up to 185% higher latency and up to 92% more virtual CPU cores for our benchmark applications -- but the severity is intimately tied to how they are configured and the application workload. The primary contributors to overhead vary based on the configuration too. IPC (inter-process communication) and socket writes dominate when the service mesh operates as a TCP proxy, but protocol parsing dominates when it operates as an HTTP proxy. MeshInsight also enables us to study the end-to-end impact of optimizations to service meshes. We show that not all seemingly-promising optimizations lead to a notable overhead reduction in realistic settings.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network. Existing machine learning inference platforms typically assume a homogeneous infrastructure and do not take into account the more complex and tiered computing infrastructure that includes edge devices, local hubs, edge datacenters, and cloud datacenters. On the other hand, recent AutoML efforts have provided viable solutions for model compression, pruning and quantization for heterogeneous environments; for a machine learning model, now we may easily find or even generate a series of models with different tradeoffs between accuracy and efficiency. We design and implement JellyBean, a system for serving and optimizing machine learning inference workflows on heterogeneous infrastructures. Given service-level objectives (e.g., throughput, accuracy), JellyBean picks the most cost-efficient models that meet the accuracy target and decides how to deploy them across different tiers of infrastructures. Evaluations show that JellyBean reduces the total serving cost of visual question answering by up to 58%, and vehicle tracking from the NVIDIA AI City Challenge by up to 36% compared with state-of-the-art model selection and worker assignment solutions. JellyBean also outperforms prior ML serving systems (e.g., Spark on the cloud) up to 5x in serving costs.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

High Velocity Kernel File Systems with Bento

High development velocity is critical for modern systems. This is especially true for Linux file systems which are seeing increased pressure from new storage devices and new demands on storage systems. However, high velocity Linux kernel development is challenging due to the ease of introducing bugs, the difficulty of testing and debugging, and the lack of support for redeployment without service disruption. Existing approaches to high-velocity development of file systems for Linux have major downsides, such as the high performance penalty for FUSE file systems, slowing the deployment cycle for new file system functionality. We propose Bento, a framework for high velocity development of Linux kernel file systems. It enables file systems written in safe Rust to be installed in the Linux kernel, with errors largely sandboxed to the file system. Bento file systems can be replaced with no disruption to running applications, allowing daily or weekly upgrades in a cloud server setting. Bento also supports userspace debugging. We implement a simple file system using Bento and show that it performs similarly to VFS-native ext4 on a variety of benchmarks and outperforms a FUSE version by 7x on 'git clone'. We also show that we can dynamically add file provenance tracking to a running kernel file system with only 15ms of service interruption.

0 citations0 reviewsNo code linkedOpen access