Early-stage Rust drop-in alternative frontend for vLLM

Tools for Python coroutines and advanced scheduling for `asyncio`

TPU inference for vLLM, with unified JAX and PyTorch support.

Achieve state of the art inference performance with modern accelerators on Kubernetes

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

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

High-performance netty and thrift-based microservice RPC library for Java

Distributed Model Serving Framework

Controller for ModelMesh

Abstracted helper classes providing consistent key-value store functionality, with zookeeper and etcd3 implementations

Fake XRandR configurations for multi-head setups with crappy video drivers, like fakexinerama but with xrandr

Java utilities for working with CompletionStages

Netty project - an event-driven asynchronous network application framework

The Java gRPC implementation. HTTP/2 based RPC