Kante Yin's repositories
enhancements
Enhancements tracking repo for Kubernetes
koordinator
QoS based scheduling system for hybrid orchestration workloads on Kubernetes, bringing workloads the best layout and status.
kubernetes
Production-Grade Container Scheduling and Management
LlamaIndex-k8s
RAG system build on top of LlamaIndex.
scheduler-plugins
Repository for out-of-tree scheduler plugins based on scheduler framework.
SubscribeIt
What we presented in our channel, like slides, learning materials, etc.. Subscribe it if you like.
test-infra
Test infrastructure for the Kubernetes project.
Awesome-LLMOps
🎉 An awesome & curated list of best LLMOps tools.
go-gpuallocator
Go Abstraction for Allocating NVIDIA GPUs with Custom Policies
goleak
Goroutine leak detector
inftyai-community
The InftyAI community.
k8s-device-plugin
NVIDIA device plugin for Kubernetes
k8s-dra-driver
Dynamic Resource Allocation (DRA) for NVIDIA GPUs in Kubernetes
kserve
Standardized Serverless ML Inference Platform on Kubernetes
llmaz-operator
A Kubernetes operator helps to manage Llmaz gracefully.
llmlite
A library helps to communicate with all kinds of LLMs consistently.
lws
LeaderWorkerSet: An API for deploying a group of pods as a unit of replication
PR-Copilot
Your AI pair programmer 🤖️ specialized in code review, code summary and even code completion. 🧑💻🐛
text-generation-inference
Large Language Model Text Generation Inference
training-operator
Training operators on Kubernetes.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
volcano
A Cloud Native Batch System (Project under CNCF)