llm-d / llm-d-benchmarkLinks
llm-d benchmark scripts and tooling
☆40Updated 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:
- Cloud Native Benchmarking of Foundation Models☆44Updated 5 months ago
- A tool to detect infrastructure issues on cloud native AI systems☆52Updated 3 months ago
- Distributed KV cache coordinator☆92Updated this week
- Inference scheduler for llm-d☆111Updated last week
- Simplified model deployment on llm-d☆28Updated 5 months ago
- InstaSlice Operator facilitates slicing of accelerators using stable APIs☆48Updated this week
- An Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.☆140Updated 2 weeks ago
- llm-d helm charts and deployment examples☆48Updated 2 weeks ago
- GenAI inference performance benchmarking tool☆137Updated last week
- Repository to demo GPU Sharing with Time Slicing, MPS, MIG and others☆55Updated last year
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆133Updated last week
- A toolkit for discovering cluster network topology.☆88Updated 2 weeks ago
- Helm charts for llm-d☆50Updated 5 months ago
- ☆20Updated last week
- Enabling Kubernetes to make pod placement decisions with platform intelligence.☆176Updated 11 months ago
- Incubating P/D sidecar for llm-d☆16Updated last month
- Variant optimization autoscaler for distributed inference workloads☆22Updated this week
- Example DRA driver that developers can fork and modify to get them started writing their own.☆110Updated 2 months ago
- WG Serving☆32Updated 2 weeks ago
- JobSet: a k8s native API for distributed ML training and HPC workloads☆291Updated last week
- Holistic job manager on Kubernetes☆115Updated last year
- Health checks for Azure N- and H-series VMs.☆55Updated 2 weeks ago
- A light weight vLLM simulator, for mocking out replicas.☆68Updated this week
- Gateway API Inference Extension☆550Updated this week
- NVIDIA DRA Driver for GPUs☆523Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆351Updated this week
- ☆273Updated 3 weeks ago
- NVIDIA NCCL Tests for Distributed Training☆130Updated last week
- Test Orchestrator for Performance and Scalability of AI pLatforms☆16Updated last week
- knavigator is a development, testing, and optimization toolkit for AI/ML scheduling systems at scale on Kubernetes.☆73Updated 5 months ago