llm-d / llm-d-benchmarkLinks
llm-d benchmark scripts and tooling
☆36Updated last week
Alternatives and similar repositories for llm-d-benchmark
Users that are interested in llm-d-benchmark are comparing it to the libraries listed below
Sorting:
- A tool to detect infrastructure issues on cloud native AI systems☆52Updated 2 months ago
- GenAI inference performance benchmarking tool☆134Updated last week
- InstaSlice Operator facilitates slicing of accelerators using stable APIs☆48Updated this week
- Cloud Native Benchmarking of Foundation Models☆44Updated 4 months ago
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆140Updated last week
- llm-d helm charts and deployment examples☆47Updated 2 weeks ago
- Incubating P/D sidecar for llm-d☆16Updated 3 weeks ago
- Inference scheduler for llm-d☆109Updated last week
- ☆20Updated last week
- Helm charts for llm-d☆50Updated 4 months ago
- Simplified model deployment on llm-d☆27Updated 5 months ago
- Repository to demo GPU Sharing with Time Slicing, MPS, MIG and others☆54Updated last year
- Enabling Kubernetes to make pod placement decisions with platform intelligence.☆176Updated 10 months ago
- Distributed KV cache coordinator☆91Updated last week
- WG Serving☆31Updated last month
- A toolkit for discovering cluster network topology.☆84Updated last week
- Gateway API Inference Extension☆537Updated this week
- Holistic job manager on Kubernetes☆115Updated last year
- Cloud Native Artifacial Intelligence Model Format Specification☆147Updated last week
- Health checks for Azure N- and H-series VMs.☆55Updated last week
- A light weight vLLM simulator, for mocking out replicas.☆59Updated last week
- Example DRA driver that developers can fork and modify to get them started writing their own.☆109Updated last month
- JobSet: a k8s native API for distributed ML training and HPC workloads☆286Updated last week
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆119Updated this week
- InstaSlice facilitates the use of Dynamic Resource Allocation (DRA) on Kubernetes clusters for GPU sharing☆30Updated last year
- ☆40Updated this week
- Intent Driven Orchestration enables management of applications through their Service Level Objectives, while minimizing developer and adm…☆46Updated 3 weeks ago
- A collection of community maintained NRI plugins