SDK for creating Hugging Face Inference Endpoints deployments

Inference server benchmarking tool

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

GPUd automates monitoring, diagnostics, and issue identification for GPUs

Minimalistic large language model 3D-parallelism training

Large Language Model Text Generation Inference

LSP server leveraging LLMs for code completion (and more?)

Home of StarCoder: fine-tuning & inference!

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

The official Python client for the Huggingface Hub.

A PyTorch-based Speech Toolkit

Fork of NVIDIA device plugin for Kubernetes with support for shared GPUs by declaring GPUs multiple times

Interpret Machine Learning black-box models deployed on Serving Engine

Exposes a serialized machine learning model through a HTTP API.

Erlenmeyer is a proxy used to parse common Open Source TimeSeries DataBase query endpoints like OpenTSDB, Prometheus/PromQL, InfluxQL or Graphite. Parsed queries are translated into WarpScript to p…

Stateful Functions for Apache Flink

Kubernetes autoscaler for deployments that consume queue in RMQ

Java Evaluator API for PMML

Desktop python client for using OVH Prescience service