GenAI inference performance benchmarking tool
☆212Jul 24, 2026Updated this week
Alternatives and similar repositories for inference-perf
Users that are interested in inference-perf are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- llm-d benchmark scripts and tooling☆62Updated this week
- Gateway API Inference Extension☆723Updated this week
- WG Serving☆38Mar 24, 2026Updated 4 months ago
- LeaderWorkerSet: An API for deploying a group of pods as a unit of replication☆769Updated this week
- Variant optimization autoscaler for distributed inference workloads☆52Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- llm-d helm charts and deployment examples☆59May 1, 2026Updated 2 months ago
- llm-d Router: The intelligent entry point for inference requests☆269Updated this week
- Achieve state of the art inference performance with modern accelerators on Kubernetes☆3,875Updated this week
- Kubernetes APIServer 高性能代理组件，代理 APIServer 的 List 请求，其它类型的请求会直接反向代理到原生 APIServer。 CKube 还额外支持了分页、搜索和索引等功能。 并且，CKube 100% 兼容原生 kubectl 和 ku…☆19Sep 16, 2022Updated 3 years ago
- Distributed KV cache scheduling & offloading libraries☆164Updated this week
- Kubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping☆16Updated this week
- ☆22Mar 11, 2026Updated 4 months ago
- An Envoy inspired, ultimate LLM-first gateway for LLM serving and downstream application developers and enterprises☆27Apr 24, 2025Updated last year
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆482Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Example DRA driver that developers can fork and modify to get them started writing their own.☆136Updated this week
- Incubating P/D sidecar for llm-d☆17Nov 13, 2025Updated 8 months ago
- Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling☆244Updated this week
- DRA Driver for NVIDIA GPUs☆677Updated this week
- KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale☆1,409Updated this week
- CPU DRA Driver☆59Updated this week
- Following the same workflows as Kubernetes. Widely used in InftyAI community.☆13May 31, 2026Updated last month
- A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual h…☆170Updated this week
- DRANET is a Kubernetes Network Driver that uses Dynamic Resource Allocation (DRA) to deliver high-performance networking for demanding ap…☆130Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A workload for deploying LLM inference services on Kubernetes☆263Updated this week
- Kubernetes-native Job Queueing☆2,747Updated this week
- Simplified Data Management and Sharing for Kubernetes☆18Updated this week
- ⚡ Guidance, samples, and tools for HPC workloads on AKS clusters with RDMA and InfiniBand support, including GPUDirect RDMA.☆23Updated this week
- DRANET is a Kubernetes Network Driver that uses Dynamic Resource Allocation (DRA) to deliver high-performance networking for demanding ap…☆160Dec 9, 2025Updated 7 months ago
- Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs☆1,429Updated this week
- ☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!☆309Jan 26, 2026Updated 6 months ago
- The main purpose of runtime copilot is to assist with node runtime management tasks such as configuring registries, upgrading versions, i…☆13May 16, 2023Updated 3 years ago
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆91Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- This project is designed to simulate GPU information, making it easier to test scenarios where a GPU is not available.☆65Jan 9, 2026Updated 6 months ago
- NVIDIA Inference Xfer Library (NIXL)☆1,151Updated this week
- Simplified model deployment on llm-d☆29Jul 2, 2025Updated last year
- Cloud Native Benchmarking of Foundation Models☆46Jul 31, 2025Updated 11 months ago
- Command-line tools for managing OCI model artifacts, which are bundled based on Model Spec☆78Updated this week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆2,474Updated this week
- An Open Standard for Packaging, Distributing and Running LLMs in Cloud-Native Environments☆218Updated this week