llm-d-incubation / workload-variant-autoscalerLinks
Variant optimization autoscaler for distributed inference workloads
☆21Updated last week
Alternatives and similar repositories for workload-variant-autoscaler
Users that are interested in workload-variant-autoscaler are comparing it to the libraries listed below
Sorting:
- Inference scheduler for llm-d☆110Updated this week
- A toolkit for discovering cluster network topology.☆86Updated last week
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆141Updated this week
- Holistic job manager on Kubernetes☆115Updated last year
- Simplified model deployment on llm-d☆28Updated 5 months ago
- llm-d benchmark scripts and tooling☆39Updated this week
- Cloud Native Artifacial Intelligence Model Format Specification☆156Updated this week
- Distributed KV cache coordinator☆92Updated this week
- ☆179Updated this week
- InstaSlice Operator facilitates slicing of accelerators using stable APIs☆48Updated last week
- GenAI inference performance benchmarking tool☆137Updated this week
- Example DRA driver that developers can fork and modify to get them started writing their own.☆110Updated last month
- Enabling Kubernetes to make pod placement decisions with platform intelligence.☆176Updated 10 months ago
- Helm charts for llm-d☆50Updated 5 months ago
- Kubernetes-native AI serving platform for scalable model serving.☆93Updated this week
- Incubating P/D sidecar for llm-d☆16Updated last month
- WG Serving☆32Updated last week
- llm-d helm charts and deployment examples☆48Updated last week
- JobSet: a k8s native API for distributed ML training and HPC workloads☆289Updated last week
- knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.☆72Updated 5 months ago
- ☆30Updated 3 months ago
- ☆33Updated this week
- Command-line tools for managing OCI model artifacts, which are bundled based on Model Spec☆54Updated last week
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆131Updated this week
- A collection of community maintained NRI plugins☆100Updated last week
- A light weight vLLM simulator, for mocking out replicas.☆65Updated this week
- ☆273Updated last week
- 🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.☆33Updated last week
- Repository to demo GPU Sharing with Time Slicing, MPS, MIG and others☆54Updated last year
- Test Orchestrator for Performance and Scalability of AI pLatforms☆16Updated this week