A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

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

AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.

A Datacenter Scale Distributed Inference Serving Framework

slime is an LLM post-training framework for RL Scaling.

Manage stacked Git branches

Unified high-performance Python client for object and file stores.

Track how much time you spend using Claude Code to AI-code

Terminal fireworks show - ASCII art celebration in your terminal

Apache Pulsar Go Client Library

PyTorch-native post-training at scale

OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

Helm charts for KEDA

Orchestrated process and container checkpointing

Terraform Helm provider