Starred repositories
Underlay and RDMA network solution of the Kubernetes, for bare metal, VM and any public cloud
Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes
A collection of Data & AI research or white papers for learning and researching across partners
1
Updated Jun 10, 2024
Development repository for the Triton language and compiler
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
This repository stores a collection of LLMs and Multimodal AI research papers for learning and researching.
1
Updated Aug 13, 2024
AI CodePlaybook contains a series of POVs for iMelonArt's AI MVP and help community create AI SaaS solutions with cloud-native technologies
A Generic Low-Code Framework Built on a Config-Driven Tree Walker
cloudmelon / ml-ferret
Forked from apple/ml-ferretBuilding Ferret multimodality open-source AI on Kubernetes
Large Language Model Text Generation Inference
cloudmelon / mistral-common
Forked from mistralai/mistral-commonMistral AI test for commercial licenses and open-source for sovereign air-gapped solutions.
Official inference library for pre-processing of Mistral models
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
12 Weeks, 24 Lessons, AI for All!
AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community. Our intent is to present a curated collection of solution ac…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
QLoRA: Efficient Finetuning of Quantized LLMs
DSPy: The framework for programming—not prompting—language models
Microsoft Official Build Modern AI Apps reference solutions and content. Demonstrate how to build Copilot applications that incorporate Hero Azure Services including Azure OpenAI Service, Azure Con…