Stars
Gateway API Inference Extension
Implementation for FP8/INT8 Rollout for RL training without performence drop.
CADAM is the open source text-to-CAD web application
Achieve state of the art inference performance with modern accelerators on Kubernetes
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
gRPC proxy is a Go reverse proxy that allows for rich routing of gRPC calls with minimum overhead.
Write scalable load tests in plain Python 🚗💨
An archive-less dockerTools.buildImage implementation
🚀 gnet is a high-performance, lightweight, non-blocking, event-driven networking framework written in pure Go.
Flax is a neural network library for JAX that is designed for flexibility.
LeaderWorkerSet: An API for deploying a group of pods as a unit of replication
Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
Lightweight, CRD based envoy control plane for kubernetes
A model checker for implementing distributed systems.
Kubernetes-like control planes for form-factors and use-cases beyond Kubernetes and container workloads.
Fast JSON encoder/decoder compatible with encoding/json for Go
The live data layer for apps and AI agents. Create up-to-the-second views into your business, just using SQL
Go package containing implementations of efficient encoding, decoding, and validation APIs.
A scalable overlay networking tool with a focus on performance, simplicity and security
The self-managing, auto-upgrading, Kubernetes distribution for everyone
A high-performance observability data pipeline.