llm-d-incubation / llm-d-infraLinks
llm-d helm charts and deployment examples
☆45Updated last month
Alternatives and similar repositories for llm-d-infra
Users that are interested in llm-d-infra are comparing it to the libraries listed below
Sorting:
- GenAI inference performance benchmarking tool☆110Updated last week
- Example DRA driver that developers can fork and modify to get them started writing their own.☆100Updated 2 weeks ago
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆134Updated this week
- Gateway API Inference Extension☆514Updated this week
- Simplified model deployment on llm-d☆27Updated 4 months ago
- ☆159Updated 3 weeks ago
- WG Serving☆31Updated 3 weeks ago
- InstaSlice Operator facilitates slicing of accelerators using stable APIs☆47Updated this week
- Cloud Native Artifacial Intelligence Model Format Specification☆116Updated this week
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replication☆611Updated this week
- knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.☆71Updated 3 months ago
- Helm charts for llm-d☆50Updated 3 months ago
- JobSet: a k8s native API for distributed ML training and HPC workloads☆279Updated this week
- Holistic job manager on Kubernetes☆116Updated last year
- ☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!☆264Updated last week
- NVIDIA DRA Driver for GPUs☆477Updated last week
- agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.☆135Updated this week
- Incubating P/D sidecar for llm-d☆16Updated last week
- ☆179Updated 3 weeks ago
- Inference scheduler for llm-d☆103Updated this week
- Distributed KV cache coordinator☆82Updated 2 weeks ago
- The main purpose of runtime copilot is to assist with node runtime management tasks such as configuring registries, upgrading versions, i…☆12Updated 2 years ago
- CAPK is a provider for Cluster API (CAPI) that allows users to deploy fake, Kubemark-backed machines to their clusters.☆82Updated 2 weeks ago
- d.run website☆15Updated this week
- Model Registry provides a single pane of glass for ML model developers to index and manage models, versions, and ML artifacts metadata. I…☆150Updated last week
- ☆66Updated this week
- 🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.☆33Updated this week
- ☆15Updated 8 months ago
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆86Updated last week
- 🏃🏿♀️🏃🏽♀️🏃🏻♂️🕒CNCF Technical Advisory Group for Runtime☆94Updated 6 months ago