Document level Attitude and Relation Extraction toolkit (AREkit) for sampling and processing large text collections with ML and for ML

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

Batch-scheduler framework for controlling execution in a packet-processing pipeline based on strict service-level objectives

Batching with python asyncio

Harmony service that groups together files into batches for concatenation

FastDynamicBatcher is a library for batching inputs across requests to accelerate machine learning workloads

Migrates public entity financial data from EDGAR zip into AWS S3 bucket

Deep Learning Autism Classification, using client-server architecture for low resource consumption & easy deployment.

Online Multiple Hypothesis Testing.

simulation of Bucket brigade in production lines.

A simple Python library for batching lists of objects

🚀 X-Model server for boosting ML inference without letting you do any heavy-lifting in the backend.

Deep Learning Stream Classification, using client-server architecture for low resource consumption & easy deployment.

Seq2Label Sentiment Analysis

Deep Learning Brand Recognition, using client-server architecture for low resource consumption & easy deployment.

Batch-aware online task creation for meta-learning.

Add watermark to one or an entire folder of images.

A comprehensive toolkit for streamlining and simplifying the offline inference process for LLMs across various models and libraries.

A distributed visit counter service, designed to efficiently track page visits with support for caching, sharding, and batching.