poussa
Follow
Lists (1)
Stars
helm charts for deploying models with llm-d
Achieve state of the art inference performance with modern accelerators on Kubernetes
llm-d benchmark scripts and tooling
Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
llm-d helm charts and deployment examples
Gateway API Inference Extension
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
Intel® AI for Enterprise RAG converts enterprise data into actionable insights with excellent TCO. Utilizing Intel Gaudi AI accelerators and Intel Xeon processors ensuring streamlined deployment.
Workload Services Framework (WSF) is a benchmarking framework on Intel(R) Xeon(R) Platforms
Terraform provider for Keycloak
GenAI Studio is a low code platform to enable users to construct, evaluate, and benchmark GenAI applications. The platform also provide capability to export developed application as a ready-to-depl…
Containerization and cloud native suite for OPEA
A repository that deploys Coder OSS entirely from TF
AWS EKS - kubernetes project and terraform module
Karpenter is a Kubernetes Node Autoscaler built for flexibility, performance, and simplicity.
Collection of Intel device plugins for Kubernetes
A collection of community maintained NRI plugins
An End-to-End Distributed and Scalable Cloud KMS (Key Management System) built on top of Intel SGX enclave-based HSM (Hardware Security Module), aka eHSM.
Production-Grade Container Scheduling and Management
This repo follows the SDS extension standard of Envoy and implements an external SDS server via more secure solution which is known as Hardware Security Module(HSM). By using this repo, User can m…
Intel QuickAssist Technology( QAT) OpenSSL Engine (an OpenSSL Plug-In Engine) which provides cryptographic acceleration for both hardware and optimized software using Intel QuickAssist Technology e…