arXiv subjects

Manish Sethi

Publications and source records attributed to Manish Sethi.

4 recordsLinked to original sources

arXiv2025

Speeding up Model Loading with fastsafetensors

The rapid increases in model parameter sizes introduces new challenges in pre-trained model loading. Currently, machine learning code often deserializes each parameter as a tensor object in host memory before copying it to device memory. We found that this approach underutilized storage throughput and significantly slowed down loading large models with a widely-used model file formats, safetensors. In this work, we present fastsafetensors, a Python library designed to optimize the deserialization of tensors in safetensors files. Our approach first copies groups of on-disk parameters to device memory, where they are directly instantiated as tensor objects. This design enables further optimization in low-level I/O and high-level tensor preprocessing, including parallelized copying, peer-to-peer DMA, and GPU offloading. Experimental results show performance improvements of 4.8x to 7.5x in loading models such as Llama (7, 13, and 70 billion parameters), Falcon (40 billion parameters), and the Bloom (176 billion parameters).

cs.DC↗

arXiv2024

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

Large Language Models (LLMs) trained on code are revolutionizing the software development process. Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously. Realizing the full potential of code LLMs requires a wide range of capabilities, including code generation, fixing bugs, explaining and documenting code, maintaining repositories, and more. In this work, we introduce the Granite series of decoder-only code models for code generative tasks, trained with code written in 116 programming languages. The Granite Code models family consists of models ranging in size from 3 to 34 billion parameters, suitable for applications ranging from complex application modernization tasks to on-device memory-constrained use cases. Evaluation on a comprehensive set of tasks demonstrates that Granite Code models consistently reaches state-of-the-art performance among available open-source code LLMs. The Granite Code model family was optimized for enterprise software development workflows and performs well across a range of coding tasks (e.g. code generation, fixing and explanation), making it a versatile all around code model. We release all our Granite Code models under an Apache 2.0 license for both research and commercial use.

cs.AI↗

arXiv2019

Blockchain Meets Database: Design and Implementation of a Blockchain Relational Database

In this paper, we design and implement the first-ever decentralized replicated relational database with blockchain properties that we term blockchain relational database. We highlight several similarities between features provided by blockchain platforms and a replicated relational database, although they are conceptually different, primarily in their trust model. Motivated by this, we leverage the rich features, decades of research and optimization, and available tooling in relational databases to build a blockchain relational database. We consider a permissioned blockchain model of known, but mutually distrustful organizations each operating their own database instance that are replicas of one another. The replicas execute transactions independently and engage in decentralized consensus to determine the commit order for transactions. We design two approaches, the first where the commit order for transactions is agreed upon prior to executing them, and the second where transactions are executed without prior knowledge of the commit order while the ordering happens in parallel. We leverage serializable snapshot isolation (SSI) to guarantee that the replicas across nodes remain consistent and respect the ordering determined by consensus, and devise a new variant of SSI based on block height for the latter approach. We implement our system on PostgreSQL and present detailed performance experiments analyzing both approaches.

cs.DC↗

arXiv2018

Hyperledger Fabric: A Distributed Operating System for Permissioned Blockchains

Fabric is a modular and extensible open-source system for deploying and operating permissioned blockchains and one of the Hyperledger projects hosted by the Linux Foundation (www.hyperledger.org). Fabric is the first truly extensible blockchain system for running distributed applications. It supports modular consensus protocols, which allows the system to be tailored to particular use cases and trust models. Fabric is also the first blockchain system that runs distributed applications written in standard, general-purpose programming languages, without systemic dependency on a native cryptocurrency. This stands in sharp contrast to existing blockchain platforms that require "smart-contracts" to be written in domain-specific languages or rely on a cryptocurrency. Fabric realizes the permissioned model using a portable notion of membership, which may be integrated with industry-standard identity management. To support such flexibility, Fabric introduces an entirely novel blockchain design and revamps the way blockchains cope with non-determinism, resource exhaustion, and performance attacks. This paper describes Fabric, its architecture, the rationale behind various design decisions, its most prominent implementation aspects, as well as its distributed application programming model. We further evaluate Fabric by implementing and benchmarking a Bitcoin-inspired digital currency. We show that Fabric achieves end-to-end throughput of more than 3500 transactions per second in certain popular deployment configurations, with sub-second latency, scaling well to over 100 peers.

cs.DC↗